id	sid	tid	token	lemma	pos
ajst-2984	1	1	academic	academic	ADJ
ajst-2984	1	2	journal	journal	NOUN
ajst-2984	1	3	of	of	ADP
ajst-2984	1	4	science	science	NOUN
ajst-2984	1	5	and	and	CCONJ
ajst-2984	1	6	technology	technology	NOUN
ajst-2984	1	7	issn	issn	NOUN
ajst-2984	1	8	:	:	PUNCT
ajst-2984	1	9	2771	2771	NUM
ajst-2984	1	10	-	-	SYM
ajst-2984	1	11	3032	3032	NUM
ajst-2984	1	12	|	|	NOUN
ajst-2984	1	13	vol	vol	NOUN
ajst-2984	1	14	.	.	PROPN
ajst-2984	2	1	3	3	NUM
ajst-2984	2	2	,	,	PUNCT
ajst-2984	2	3	no	no	INTJ
ajst-2984	2	4	.	.	NOUN
ajst-2984	2	5	3	3	NUM
ajst-2984	2	6	,	,	PUNCT
ajst-2984	2	7	2022	2022	NUM
ajst-2984	2	8	211	211	NUM
ajst-2984	2	9	construction	construction	NOUN
ajst-2984	2	10	of	of	ADP
ajst-2984	2	11	unhealthy	unhealthy	ADJ
ajst-2984	2	12	webpage	webpage	NOUN
ajst-2984	2	13	filtering	filter	VERB
ajst-2984	2	14	mode	mode	NOUN
ajst-2984	2	15	based	base	VERB
ajst-2984	2	16	on	on	ADP
ajst-2984	2	17	data	data	NOUN
ajst-2984	2	18	mining	mining	NOUN
ajst-2984	2	19	technology	technology	PROPN
ajst-2984	2	20	ronghua	ronghua	PROPN
ajst-2984	2	21	lu	lu	PROPN
ajst-2984	2	22	jingdezhen	jingdezhen	PROPN
ajst-2984	2	23	ceramic	ceramic	PROPN
ajst-2984	2	24	university	university	PROPN
ajst-2984	2	25	,	,	PUNCT
ajst-2984	2	26	jiangxi	jiangxi	NOUN
ajst-2984	2	27	,	,	PUNCT
ajst-2984	2	28	3334403	3334403	NUM
ajst-2984	2	29	,	,	PUNCT
ajst-2984	2	30	china	china	PROPN
ajst-2984	2	31	abstract	abstract	PROPN
ajst-2984	2	32	:	:	PUNCT
ajst-2984	2	33	the	the	DET
ajst-2984	2	34	unhealthy	unhealthy	ADJ
ajst-2984	2	35	category	category	NOUN
ajst-2984	2	36	eigenvector	eigenvector	NOUN
ajst-2984	2	37	library	library	NOUN
ajst-2984	2	38	is	be	AUX
ajst-2984	2	39	constructed	construct	VERB
ajst-2984	2	40	by	by	ADP
ajst-2984	2	41	adaptive	adaptive	ADJ
ajst-2984	2	42	sample	sample	NOUN
ajst-2984	2	43	library	library	NOUN
ajst-2984	2	44	,	,	PUNCT
ajst-2984	2	45	and	and	CCONJ
ajst-2984	2	46	the	the	DET
ajst-2984	2	47	unhealthy	unhealthy	ADJ
ajst-2984	2	48	category	category	NOUN
ajst-2984	2	49	model	model	NOUN
ajst-2984	2	50	is	be	AUX
ajst-2984	2	51	constructed	construct	VERB
ajst-2984	2	52	on	on	ADP
ajst-2984	2	53	this	this	DET
ajst-2984	2	54	basis	basis	NOUN
ajst-2984	2	55	to	to	PART
ajst-2984	2	56	realize	realize	VERB
ajst-2984	2	57	the	the	DET
ajst-2984	2	58	filtering	filtering	NOUN
ajst-2984	2	59	of	of	ADP
ajst-2984	2	60	unhealthy	unhealthy	ADJ
ajst-2984	2	61	webpages	webpage	NOUN
ajst-2984	2	62	.	.	PUNCT
ajst-2984	3	1	our	our	PRON
ajst-2984	3	2	expermient	expermient	NOUN
ajst-2984	3	3	proves	prove	VERB
ajst-2984	3	4	that	that	SCONJ
ajst-2984	3	5	this	this	DET
ajst-2984	3	6	mode	mode	NOUN
ajst-2984	3	7	can	can	AUX
ajst-2984	3	8	filter	filter	VERB
ajst-2984	3	9	unhealthy	unhealthy	ADJ
ajst-2984	3	10	webpage	webpage	NOUN
ajst-2984	3	11	at	at	ADP
ajst-2984	3	12	higher	high	ADJ
ajst-2984	3	13	speed	speed	NOUN
ajst-2984	3	14	and	and	CCONJ
ajst-2984	3	15	satisfying	satisfy	VERB
ajst-2984	3	16	precision	precision	NOUN
ajst-2984	3	17	.	.	PUNCT
ajst-2984	4	1	keywords	keyword	NOUN
ajst-2984	4	2	:	:	PUNCT
ajst-2984	4	3	data	datum	NOUN
ajst-2984	4	4	mining	mining	NOUN
ajst-2984	4	5	,	,	PUNCT
ajst-2984	4	6	web	web	NOUN
ajst-2984	4	7	filtering	filtering	NOUN
ajst-2984	4	8	,	,	PUNCT
ajst-2984	4	9	feature	feature	NOUN
ajst-2984	4	10	word	word	NOUN
ajst-2984	4	11	,	,	PUNCT
ajst-2984	4	12	vector	vector	NOUN
ajst-2984	4	13	space	space	NOUN
ajst-2984	4	14	model	model	NOUN
ajst-2984	4	15	,	,	PUNCT
ajst-2984	4	16	characteristic	characteristic	ADJ
ajst-2984	4	17	vector	vector	NOUN
ajst-2984	4	18	library	library	NOUN
ajst-2984	4	19	.	.	PUNCT
ajst-2984	5	1	1	1	X
ajst-2984	5	2	.	.	X
ajst-2984	5	3	introduction	introduction	NOUN
ajst-2984	5	4	internet	internet	NOUN
ajst-2984	5	5	technology	technology	NOUN
ajst-2984	5	6	has	have	AUX
ajst-2984	5	7	made	make	VERB
ajst-2984	5	8	the	the	DET
ajst-2984	5	9	sharing	sharing	NOUN
ajst-2984	5	10	and	and	CCONJ
ajst-2984	5	11	release	release	NOUN
ajst-2984	5	12	of	of	ADP
ajst-2984	5	13	information	information	NOUN
ajst-2984	5	14	across	across	ADP
ajst-2984	5	15	the	the	DET
ajst-2984	5	16	limitations	limitation	NOUN
ajst-2984	5	17	of	of	ADP
ajst-2984	5	18	time	time	NOUN
ajst-2984	5	19	and	and	CCONJ
ajst-2984	5	20	space	space	NOUN
ajst-2984	5	21	.	.	PUNCT
ajst-2984	6	1	internet	internet	NOUN
ajst-2984	6	2	has	have	AUX
ajst-2984	6	3	become	become	VERB
ajst-2984	6	4	an	an	DET
ajst-2984	6	5	important	important	ADJ
ajst-2984	6	6	source	source	NOUN
ajst-2984	6	7	of	of	ADP
ajst-2984	6	8	information	information	NOUN
ajst-2984	6	9	for	for	SCONJ
ajst-2984	6	10	people	people	NOUN
ajst-2984	6	11	to	to	PART
ajst-2984	6	12	obtain	obtain	VERB
ajst-2984	6	13	information	information	NOUN
ajst-2984	6	14	.	.	PUNCT
ajst-2984	7	1	while	while	SCONJ
ajst-2984	7	2	internet	internet	NOUN
ajst-2984	7	3	has	have	AUX
ajst-2984	7	4	brought	bring	VERB
ajst-2984	7	5	us	we	PRON
ajst-2984	7	6	information	information	NOUN
ajst-2984	7	7	explosion	explosion	NOUN
ajst-2984	7	8	and	and	CCONJ
ajst-2984	7	9	rapid	rapid	ADJ
ajst-2984	7	10	economy	economy	NOUN
ajst-2984	7	11	,	,	PUNCT
ajst-2984	7	12	it	it	PRON
ajst-2984	7	13	has	have	AUX
ajst-2984	7	14	also	also	ADV
ajst-2984	7	15	brought	bring	VERB
ajst-2984	7	16	a	a	DET
ajst-2984	7	17	lot	lot	NOUN
ajst-2984	7	18	of	of	ADP
ajst-2984	7	19	unhealthy	unhealthy	ADJ
ajst-2984	7	20	information	information	NOUN
ajst-2984	7	21	that	that	PRON
ajst-2984	7	22	is	be	AUX
ajst-2984	7	23	not	not	PART
ajst-2984	7	24	conducive	conducive	ADJ
ajst-2984	7	25	to	to	ADP
ajst-2984	7	26	economic	economic	ADJ
ajst-2984	7	27	development	development	NOUN
ajst-2984	7	28	and	and	CCONJ
ajst-2984	7	29	people	people	NOUN
ajst-2984	7	30	's	's	PART
ajst-2984	7	31	lives	life	NOUN
ajst-2984	7	32	.	.	PUNCT
ajst-2984	8	1	for	for	ADP
ajst-2984	8	2	example	example	NOUN
ajst-2984	8	3	,	,	PUNCT
ajst-2984	8	4	various	various	ADJ
ajst-2984	8	5	unhealthy	unhealthy	ADJ
ajst-2984	8	6	texts	text	NOUN
ajst-2984	8	7	(	(	PUNCT
ajst-2984	8	8	pornography	pornography	NOUN
ajst-2984	8	9	,	,	PUNCT
ajst-2984	8	10	violence	violence	NOUN
ajst-2984	8	11	,	,	PUNCT
ajst-2984	8	12	reactionary	reactionary	ADJ
ajst-2984	8	13	)	)	PUNCT
ajst-2984	8	14	on	on	ADP
ajst-2984	8	15	internet	internet	NOUN
ajst-2984	8	16	are	be	AUX
ajst-2984	8	17	flooding	flood	VERB
ajst-2984	8	18	.	.	PUNCT
ajst-2984	9	1	how	how	SCONJ
ajst-2984	9	2	to	to	PART
ajst-2984	9	3	effectively	effectively	ADV
ajst-2984	9	4	filter	filter	VERB
ajst-2984	9	5	unhealthy	unhealthy	ADJ
ajst-2984	9	6	webpages	webpage	NOUN
ajst-2984	9	7	and	and	CCONJ
ajst-2984	9	8	give	give	VERB
ajst-2984	9	9	network	network	NOUN
ajst-2984	9	10	users	user	NOUN
ajst-2984	9	11	a	a	DET
ajst-2984	9	12	‘	'	PUNCT
ajst-2984	9	13	green’space	green’space	NOUN
ajst-2984	9	14	is	be	AUX
ajst-2984	9	15	an	an	DET
ajst-2984	9	16	urgent	urgent	ADJ
ajst-2984	9	17	problem	problem	NOUN
ajst-2984	9	18	to	to	PART
ajst-2984	9	19	be	be	AUX
ajst-2984	9	20	solved	solve	VERB
ajst-2984	9	21	.	.	PUNCT
ajst-2984	10	1	2	2	X
ajst-2984	10	2	.	.	X
ajst-2984	10	3	text	text	NOUN
ajst-2984	10	4	representation	representation	NOUN
ajst-2984	10	5	and	and	CCONJ
ajst-2984	10	6	characteristic	characteristic	ADJ
ajst-2984	10	7	vector	vector	NOUN
ajst-2984	10	8	libraries	library	NOUN
ajst-2984	10	9	the	the	DET
ajst-2984	10	10	current	current	ADJ
ajst-2984	10	11	widely	widely	ADV
ajst-2984	10	12	used	use	VERB
ajst-2984	10	13	text	text	NOUN
ajst-2984	10	14	representation	representation	NOUN
ajst-2984	10	15	models	model	NOUN
ajst-2984	10	16	are	be	AUX
ajst-2984	10	17	:	:	PUNCT
ajst-2984	10	18	boolean	boolean	ADJ
ajst-2984	10	19	model	model	NOUN
ajst-2984	10	20	,	,	PUNCT
ajst-2984	10	21	probability	probability	NOUN
ajst-2984	10	22	model	model	NOUN
ajst-2984	10	23	and	and	CCONJ
ajst-2984	10	24	vector	vector	NOUN
ajst-2984	10	25	space	space	NOUN
ajst-2984	10	26	model	model	NOUN
ajst-2984	10	27	.	.	PUNCT
ajst-2984	11	1	in	in	ADP
ajst-2984	11	2	this	this	DET
ajst-2984	11	3	paper	paper	NOUN
ajst-2984	11	4	,	,	PUNCT
ajst-2984	11	5	we	we	PRON
ajst-2984	11	6	use	use	VERB
ajst-2984	11	7	the	the	DET
ajst-2984	11	8	vector	vector	NOUN
ajst-2984	11	9	space	space	NOUN
ajst-2984	11	10	model	model	NOUN
ajst-2984	11	11	,	,	PUNCT
ajst-2984	11	12	each	each	DET
ajst-2984	11	13	document	document	NOUN
ajst-2984	11	14	is	be	AUX
ajst-2984	11	15	regarded	regard	VERB
ajst-2984	11	16	as	as	ADP
ajst-2984	11	17	a	a	DET
ajst-2984	11	18	vector	vector	NOUN
ajst-2984	11	19	composed	compose	VERB
ajst-2984	11	20	of	of	ADP
ajst-2984	11	21	items	item	NOUN
ajst-2984	11	22	(	(	PUNCT
ajst-2984	11	23	composed	compose	VERB
ajst-2984	11	24	of	of	ADP
ajst-2984	11	25	seperate	seperate	ADJ
ajst-2984	11	26	word	word	NOUN
ajst-2984	11	27	,	,	PUNCT
ajst-2984	11	28	words	word	NOUN
ajst-2984	11	29	or	or	CCONJ
ajst-2984	11	30	phrases	phrase	NOUN
ajst-2984	11	31	)	)	PUNCT
ajst-2984	11	32	,	,	PUNCT
ajst-2984	11	33	these	these	DET
ajst-2984	11	34	items	item	NOUN
ajst-2984	11	35	are	be	AUX
ajst-2984	11	36	called	call	VERB
ajst-2984	11	37	the	the	DET
ajst-2984	11	38	dimension	dimension	NOUN
ajst-2984	11	39	of	of	ADP
ajst-2984	11	40	the	the	DET
ajst-2984	11	41	vector	vector	NOUN
ajst-2984	11	42	;	;	PUNCT
ajst-2984	11	43	the	the	DET
ajst-2984	11	44	document	document	NOUN
ajst-2984	11	45	set	set	NOUN
ajst-2984	11	46	is	be	AUX
ajst-2984	11	47	regarded	regard	VERB
ajst-2984	11	48	as	as	ADP
ajst-2984	11	49	a	a	DET
ajst-2984	11	50	vector	vector	NOUN
ajst-2984	11	51	space	space	NOUN
ajst-2984	11	52	composed	compose	VERB
ajst-2984	11	53	of	of	ADP
ajst-2984	11	54	documents	document	NOUN
ajst-2984	11	55	.	.	PUNCT
ajst-2984	12	1	in	in	ADP
ajst-2984	12	2	the	the	DET
ajst-2984	12	3	vector	vector	NOUN
ajst-2984	12	4	space	space	NOUN
ajst-2984	12	5	model	model	NOUN
ajst-2984	12	6	,	,	PUNCT
ajst-2984	12	7	each	each	DET
ajst-2984	12	8	document	document	NOUN
ajst-2984	12	9	is	be	AUX
ajst-2984	12	10	represented	represent	VERB
ajst-2984	12	11	by	by	ADP
ajst-2984	12	12	vector	vector	NOUN
ajst-2984	12	13	,	,	PUNCT
ajst-2984	12	14	and	and	CCONJ
ajst-2984	12	15	the	the	DET
ajst-2984	12	16	dimension	dimension	NOUN
ajst-2984	12	17	of	of	ADP
ajst-2984	12	18	the	the	DET
ajst-2984	12	19	vector	vector	NOUN
ajst-2984	12	20	is	be	AUX
ajst-2984	12	21	the	the	DET
ajst-2984	12	22	number	number	NOUN
ajst-2984	12	23	of	of	ADP
ajst-2984	12	24	elements	element	NOUN
ajst-2984	12	25	in	in	ADP
ajst-2984	12	26	these	these	DET
ajst-2984	12	27	item	item	NOUN
ajst-2984	12	28	sets	set	NOUN
ajst-2984	12	29	.	.	PUNCT
ajst-2984	13	1	document	document	NOUN
ajst-2984	13	2	d	d	NOUN
ajst-2984	13	3	can	can	AUX
ajst-2984	13	4	be	be	AUX
ajst-2984	13	5	expressed	express	VERB
ajst-2984	13	6	as	as	ADP
ajst-2984	13	7	d	d	NOUN
ajst-2984	13	8	=	=	NOUN
ajst-2984	13	9	d(t1,t2,	d(t1,t2,	NOUN
ajst-2984	13	10	…	…	SYM
ajst-2984	13	11	…	…	X
ajst-2984	13	12	,tn	,tn	NUM
ajst-2984	13	13	)	)	PUNCT
ajst-2984	13	14	,	,	PUNCT
ajst-2984	13	15	where	where	SCONJ
ajst-2984	13	16	tk	tk	PROPN
ajst-2984	13	17	is	be	AUX
ajst-2984	13	18	a	a	DET
ajst-2984	13	19	character	character	NOUN
ajst-2984	13	20	item,1≤k≤n	item,1≤k≤n	NOUN
ajst-2984	13	21	.	.	PUNCT
ajst-2984	14	1	for	for	ADP
ajst-2984	14	2	a	a	DET
ajst-2984	14	3	document	document	NOUN
ajst-2984	14	4	with	with	ADP
ajst-2984	14	5	n	n	ADP
ajst-2984	14	6	items	item	NOUN
ajst-2984	14	7	,	,	PUNCT
ajst-2984	14	8	the	the	DET
ajst-2984	14	9	item	item	NOUN
ajst-2984	14	10	tk	tk	PROPN
ajst-2984	14	11	is	be	AUX
ajst-2984	14	12	often	often	ADV
ajst-2984	14	13	given	give	VERB
ajst-2984	14	14	a	a	DET
ajst-2984	14	15	certain	certain	ADJ
ajst-2984	14	16	weight	weight	NOUN
ajst-2984	14	17	wk	wk	NOUN
ajst-2984	14	18	,	,	PUNCT
ajst-2984	14	19	indicating	indicate	VERB
ajst-2984	14	20	its	its	PRON
ajst-2984	14	21	importance	importance	NOUN
ajst-2984	14	22	in	in	ADP
ajst-2984	14	23	the	the	DET
ajst-2984	14	24	document	document	NOUN
ajst-2984	14	25	,	,	PUNCT
ajst-2984	14	26	that	that	ADV
ajst-2984	14	27	is	is	ADV
ajst-2984	14	28	,	,	PUNCT
ajst-2984	14	29	d	d	PROPN
ajst-2984	14	30	=	=	NOUN
ajst-2984	14	31	d(t1,w1	d(t1,w1	NOUN
ajst-2984	14	32	;	;	PUNCT
ajst-2984	14	33	t2,w2	t2,w2	PROPN
ajst-2984	14	34	;	;	PUNCT
ajst-2984	14	35	……	……	NOUN
ajst-2984	14	36	;	;	PUNCT
ajst-2984	14	37	tn	tn	NOUN
ajst-2984	14	38	,	,	PUNCT
ajst-2984	14	39	wn),abbreviated	wn),abbreviate	VERB
ajst-2984	14	40	as	as	ADP
ajst-2984	14	41	d	d	NOUN
ajst-2984	14	42	=	=	NOUN
ajst-2984	14	43	d(w1,w2，	d(w1,w2，	PROPN
ajst-2984	14	44	…	…	PUNCT
ajst-2984	14	45	…	…	PUNCT
ajst-2984	14	46	,wn),wk	,wn),wk	PUNCT
ajst-2984	14	47	is	be	AUX
ajst-2984	14	48	also	also	ADV
ajst-2984	14	49	called	call	VERB
ajst-2984	14	50	the	the	DET
ajst-2984	14	51	word	word	NOUN
ajst-2984	14	52	frequency	frequency	NOUN
ajst-2984	14	53	statistic	statistic	NOUN
ajst-2984	14	54	of	of	ADP
ajst-2984	14	55	the	the	DET
ajst-2984	14	56	character	character	NOUN
ajst-2984	14	57	in	in	ADP
ajst-2984	14	58	the	the	DET
ajst-2984	14	59	document	document	NOUN
ajst-2984	14	60	.	.	PUNCT
ajst-2984	15	1	in	in	ADP
ajst-2984	15	2	this	this	DET
ajst-2984	15	3	paper	paper	NOUN
ajst-2984	15	4	,	,	PUNCT
ajst-2984	15	5	the	the	DET
ajst-2984	15	6	chinese	chinese	ADJ
ajst-2984	15	7	character	character	NOUN
ajst-2984	15	8	items	item	NOUN
ajst-2984	15	9	in	in	ADP
ajst-2984	15	10	each	each	DET
ajst-2984	15	11	document	document	NOUN
ajst-2984	15	12	are	be	AUX
ajst-2984	15	13	formed	form	VERB
ajst-2984	15	14	into	into	ADP
ajst-2984	15	15	a	a	DET
ajst-2984	15	16	sequence	sequence	NOUN
ajst-2984	15	17	according	accord	VERB
ajst-2984	15	18	to	to	ADP
ajst-2984	15	19	the	the	DET
ajst-2984	15	20	order	order	NOUN
ajst-2984	15	21	of	of	ADP
ajst-2984	15	22	word	word	NOUN
ajst-2984	15	23	frequency	frequency	NOUN
ajst-2984	15	24	,	,	PUNCT
ajst-2984	15	25	and	and	CCONJ
ajst-2984	15	26	the	the	DET
ajst-2984	15	27	vector	vector	NOUN
ajst-2984	15	28	with	with	ADP
ajst-2984	15	29	the	the	DET
ajst-2984	15	30	main	main	ADJ
ajst-2984	15	31	information	information	NOUN
ajst-2984	15	32	of	of	ADP
ajst-2984	15	33	‘	'	PUNCT
ajst-2984	15	34	chinese	chinese	ADJ
ajst-2984	15	35	character	character	NOUN
ajst-2984	15	36	items	item	NOUN
ajst-2984	15	37	,	,	PUNCT
ajst-2984	15	38	word	word	NOUN
ajst-2984	15	39	frequency	frequency	NOUN
ajst-2984	15	40	and	and	CCONJ
ajst-2984	15	41	word	word	NOUN
ajst-2984	15	42	frequency	frequency	NOUN
ajst-2984	15	43	ranking’is	ranking’is	NOUN
ajst-2984	15	44	called	call	VERB
ajst-2984	15	45	‘	'	PUNCT
ajst-2984	15	46	characteristic	characteristic	ADJ
ajst-2984	15	47	vector	vector	NOUN
ajst-2984	15	48	word	word	NOUN
ajst-2984	15	49	’	'	PUNCT
ajst-2984	15	50	.	.	PUNCT
ajst-2984	16	1	that	that	PRON
ajst-2984	16	2	is	be	AUX
ajst-2984	16	3	to	to	PART
ajst-2984	16	4	say	say	VERB
ajst-2984	16	5	,	,	PUNCT
ajst-2984	16	6	characteristic	characteristic	ADJ
ajst-2984	16	7	vector	vector	NOUN
ajst-2984	16	8	word	word	NOUN
ajst-2984	16	9	is	be	AUX
ajst-2984	16	10	a	a	DET
ajst-2984	16	11	word	word	NOUN
ajst-2984	16	12	with	with	ADP
ajst-2984	16	13	multidimensional	multidimensional	ADJ
ajst-2984	16	14	information	information	NOUN
ajst-2984	16	15	such	such	ADJ
ajst-2984	16	16	as	as	ADP
ajst-2984	16	17	word	word	NOUN
ajst-2984	16	18	frequency	frequency	NOUN
ajst-2984	16	19	obtained	obtain	VERB
ajst-2984	16	20	after	after	ADP
ajst-2984	16	21	the	the	DET
ajst-2984	16	22	word	word	NOUN
ajst-2984	16	23	frequency	frequency	NOUN
ajst-2984	16	24	statistics	statistic	NOUN
ajst-2984	16	25	of	of	ADP
ajst-2984	16	26	the	the	DET
ajst-2984	16	27	document	document	NOUN
ajst-2984	16	28	set	set	NOUN
ajst-2984	16	29	,	,	PUNCT
ajst-2984	16	30	expressed	express	VERB
ajst-2984	16	31	as	as	ADP
ajst-2984	16	32	:	:	PUNCT
ajst-2984	16	33	characteristic	characteristic	ADJ
ajst-2984	16	34	vector	vector	NOUN
ajst-2984	16	35	word	word	NOUN
ajst-2984	16	36	=(	=(	NOUN
ajst-2984	16	37	character	character	NOUN
ajst-2984	16	38	items	item	NOUN
ajst-2984	16	39	,	,	PUNCT
ajst-2984	16	40	word	word	NOUN
ajst-2984	16	41	frequency	frequency	NOUN
ajst-2984	16	42	,	,	PUNCT
ajst-2984	16	43	word	word	NOUN
ajst-2984	16	44	frequency	frequency	NOUN
ajst-2984	16	45	ranking	ranking	NOUN
ajst-2984	16	46	,	,	PUNCT
ajst-2984	16	47	other	other	ADJ
ajst-2984	16	48	field	field	NOUN
ajst-2984	16	49	information	information	NOUN
ajst-2984	16	50	)	)	PUNCT
ajst-2984	16	51	.	.	PUNCT
ajst-2984	17	1	the	the	DET
ajst-2984	17	2	training	training	NOUN
ajst-2984	17	3	corpus	corpus	NOUN
ajst-2984	17	4	of	of	ADP
ajst-2984	17	5	each	each	DET
ajst-2984	17	6	category	category	NOUN
ajst-2984	17	7	is	be	AUX
ajst-2984	17	8	used	use	VERB
ajst-2984	17	9	as	as	ADP
ajst-2984	17	10	the	the	DET
ajst-2984	17	11	document	document	NOUN
ajst-2984	17	12	set	set	NOUN
ajst-2984	17	13	,	,	PUNCT
ajst-2984	17	14	and	and	CCONJ
ajst-2984	17	15	all	all	PRON
ajst-2984	17	16	of	of	ADP
ajst-2984	17	17	chinese	chinese	ADJ
ajst-2984	17	18	characters	character	NOUN
ajst-2984	17	19	appearing	appear	VERB
ajst-2984	17	20	in	in	ADP
ajst-2984	17	21	the	the	DET
ajst-2984	17	22	document	document	NOUN
ajst-2984	17	23	set	set	NOUN
ajst-2984	17	24	of	of	ADP
ajst-2984	17	25	each	each	DET
ajst-2984	17	26	category	category	NOUN
ajst-2984	17	27	,	,	PUNCT
ajst-2984	17	28	and	and	CCONJ
ajst-2984	17	29	word	word	NOUN
ajst-2984	17	30	frequency	frequency	NOUN
ajst-2984	17	31	and	and	CCONJ
ajst-2984	17	32	word	word	NOUN
ajst-2984	17	33	frequency	frequency	NOUN
ajst-2984	17	34	ranking	ranking	NOUN
ajst-2984	17	35	of	of	ADP
ajst-2984	17	36	all	all	PRON
ajst-2984	17	37	of	of	ADP
ajst-2984	17	38	document	document	NOUN
ajst-2984	17	39	sets	set	NOUN
ajst-2984	17	40	under	under	ADP
ajst-2984	17	41	the	the	DET
ajst-2984	17	42	category	category	NOUN
ajst-2984	17	43	are	be	AUX
ajst-2984	17	44	counted	count	VERB
ajst-2984	17	45	respectively	respectively	ADV
ajst-2984	17	46	,	,	PUNCT
ajst-2984	17	47	so	so	SCONJ
ajst-2984	17	48	as	as	SCONJ
ajst-2984	17	49	to	to	PART
ajst-2984	17	50	obtain	obtain	VERB
ajst-2984	17	51	characteristic	characteristic	ADJ
ajst-2984	17	52	vector	vector	NOUN
ajst-2984	17	53	library	library	NOUN
ajst-2984	17	54	of	of	ADP
ajst-2984	17	55	each	each	DET
ajst-2984	17	56	category	category	NOUN
ajst-2984	17	57	.	.	PUNCT
ajst-2984	18	1	3	3	X
ajst-2984	18	2	.	.	X
ajst-2984	18	3	creation	creation	NOUN
ajst-2984	18	4	of	of	ADP
ajst-2984	18	5	unhealthy	unhealthy	ADJ
ajst-2984	18	6	class	class	NOUN
ajst-2984	18	7	characteristic	characteristic	ADJ
ajst-2984	18	8	vector	vector	NOUN
ajst-2984	18	9	word	word	NOUN
ajst-2984	18	10	if	if	SCONJ
ajst-2984	18	11	the	the	DET
ajst-2984	18	12	word	word	NOUN
ajst-2984	18	13	frequency	frequency	NOUN
ajst-2984	18	14	value	value	NOUN
ajst-2984	18	15	of	of	ADP
ajst-2984	18	16	a	a	DET
ajst-2984	18	17	characteristic	characteristic	ADJ
ajst-2984	18	18	vector	vector	NOUN
ajst-2984	18	19	word	word	NOUN
ajst-2984	18	20	in	in	ADP
ajst-2984	18	21	the	the	DET
ajst-2984	18	22	unhealthy	unhealthy	ADJ
ajst-2984	18	23	class	class	NOUN
ajst-2984	18	24	characteristic	characteristic	ADJ
ajst-2984	18	25	vector	vector	NOUN
ajst-2984	18	26	library	library	NOUN
ajst-2984	18	27	is	be	AUX
ajst-2984	18	28	larger	large	ADJ
ajst-2984	18	29	than	than	ADP
ajst-2984	18	30	the	the	DET
ajst-2984	18	31	absolute	absolute	ADJ
ajst-2984	18	32	value	value	NOUN
ajst-2984	18	33	of	of	ADP
ajst-2984	18	34	the	the	DET
ajst-2984	18	35	word	word	NOUN
ajst-2984	18	36	frequency	frequency	NOUN
ajst-2984	18	37	value	value	NOUN
ajst-2984	18	38	in	in	ADP
ajst-2984	18	39	the	the	DET
ajst-2984	18	40	common	common	ADJ
ajst-2984	18	41	class	class	NOUN
ajst-2984	18	42	characteristic	characteristic	ADJ
ajst-2984	18	43	vector	vector	NOUN
ajst-2984	18	44	word	word	NOUN
ajst-2984	18	45	,	,	PUNCT
ajst-2984	18	46	and	and	CCONJ
ajst-2984	18	47	it	it	PRON
ajst-2984	18	48	belongs	belong	VERB
ajst-2984	18	49	to	to	ADP
ajst-2984	18	50	the	the	DET
ajst-2984	18	51	non	non	ADJ
ajst-2984	18	52	-	-	ADJ
ajst-2984	18	53	stop	stop	ADJ
ajst-2984	18	54	vector	vector	NOUN
ajst-2984	18	55	word	word	NOUN
ajst-2984	18	56	,	,	PUNCT
ajst-2984	18	57	it	it	PRON
ajst-2984	18	58	is	be	AUX
ajst-2984	18	59	considered	consider	VERB
ajst-2984	18	60	that	that	SCONJ
ajst-2984	18	61	the	the	DET
ajst-2984	18	62	vector	vector	NOUN
ajst-2984	18	63	word	word	NOUN
ajst-2984	18	64	has	have	VERB
ajst-2984	18	65	a	a	DET
ajst-2984	18	66	strong	strong	ADJ
ajst-2984	18	67	unhealthy	unhealthy	ADJ
ajst-2984	18	68	tendency	tendency	NOUN
ajst-2984	18	69	,	,	PUNCT
ajst-2984	18	70	which	which	PRON
ajst-2984	18	71	is	be	AUX
ajst-2984	18	72	called	call	VERB
ajst-2984	18	73	the	the	DET
ajst-2984	18	74	unhealthy	unhealthy	ADJ
ajst-2984	18	75	class	class	NOUN
ajst-2984	18	76	characteristic	characteristic	ADJ
ajst-2984	18	77	vector	vector	NOUN
ajst-2984	18	78	word	word	NOUN
ajst-2984	18	79	.	.	PUNCT
ajst-2984	19	1	the	the	DET
ajst-2984	19	2	construction	construction	NOUN
ajst-2984	19	3	steps	step	NOUN
ajst-2984	19	4	of	of	ADP
ajst-2984	19	5	unhealthy	unhealthy	ADJ
ajst-2984	19	6	class	class	NOUN
ajst-2984	19	7	characteristic	characteristic	ADJ
ajst-2984	19	8	vector	vector	NOUN
ajst-2984	19	9	library	library	NOUN
ajst-2984	19	10	can	can	AUX
ajst-2984	19	11	be	be	AUX
ajst-2984	19	12	summarized	summarize	VERB
ajst-2984	19	13	as	as	ADP
ajst-2984	19	14	:	:	PUNCT
ajst-2984	19	15	1)construct	1)construct	NUM
ajst-2984	19	16	the	the	DET
ajst-2984	19	17	characteristic	characteristic	ADJ
ajst-2984	19	18	vector	vector	NOUN
ajst-2984	19	19	library	library	NOUN
ajst-2984	19	20	of	of	ADP
ajst-2984	19	21	common	common	ADJ
ajst-2984	19	22	classes	class	NOUN
ajst-2984	19	23	;	;	PUNCT
ajst-2984	19	24	2)construct	2)construct	NUM
ajst-2984	19	25	the	the	DET
ajst-2984	19	26	characteristic	characteristic	ADJ
ajst-2984	19	27	vector	vector	NOUN
ajst-2984	19	28	library	library	NOUN
ajst-2984	19	29	of	of	ADP
ajst-2984	19	30	unhealthy	unhealthy	ADJ
ajst-2984	19	31	classes	class	NOUN
ajst-2984	19	32	;	;	PUNCT
ajst-2984	19	33	3)by	3)by	NUM
ajst-2984	19	34	comparing	compare	VERB
ajst-2984	19	35	common	common	ADJ
ajst-2984	19	36	class	class	NOUN
ajst-2984	19	37	characteristic	characteristic	ADJ
ajst-2984	19	38	vector	vector	NOUN
ajst-2984	19	39	library	library	NOUN
ajst-2984	19	40	and	and	CCONJ
ajst-2984	19	41	unhealthy	unhealthy	ADJ
ajst-2984	19	42	class	class	NOUN
ajst-2984	19	43	characteristic	characteristic	ADJ
ajst-2984	19	44	vector	vector	NOUN
ajst-2984	19	45	library	library	NOUN
ajst-2984	19	46	,	,	PUNCT
ajst-2984	19	47	extracting	extract	VERB
ajst-2984	19	48	the	the	DET
ajst-2984	19	49	characteristic	characteristic	ADJ
ajst-2984	19	50	vector	vector	NOUN
ajst-2984	19	51	with	with	ADP
ajst-2984	19	52	large	large	ADJ
ajst-2984	19	53	absolute	absolute	ADJ
ajst-2984	19	54	difference	difference	NOUN
ajst-2984	19	55	of	of	ADP
ajst-2984	19	56	word	word	NOUN
ajst-2984	19	57	frequency	frequency	NOUN
ajst-2984	19	58	and	and	CCONJ
ajst-2984	19	59	it	it	PRON
ajst-2984	19	60	's	be	AUX
ajst-2984	19	61	not	not	PART
ajst-2984	19	62	belong	belong	ADJ
ajst-2984	19	63	to	to	PART
ajst-2984	19	64	stop	stop	VERB
ajst-2984	19	65	vector	vector	NOUN
ajst-2984	19	66	word	word	NOUN
ajst-2984	19	67	;	;	PUNCT
ajst-2984	19	68	after	after	ADP
ajst-2984	19	69	constructing	construct	VERB
ajst-2984	19	70	common	common	ADJ
ajst-2984	19	71	class	class	NOUN
ajst-2984	19	72	characteristic	characteristic	ADJ
ajst-2984	19	73	vector	vector	NOUN
ajst-2984	19	74	library	library	NOUN
ajst-2984	19	75	and	and	CCONJ
ajst-2984	19	76	unhealthy	unhealthy	ADJ
ajst-2984	19	77	class	class	NOUN
ajst-2984	19	78	characteristic	characteristic	ADJ
ajst-2984	19	79	vector	vector	NOUN
ajst-2984	19	80	library	library	NOUN
ajst-2984	19	81	,	,	PUNCT
ajst-2984	19	82	the	the	DET
ajst-2984	19	83	creation	creation	NOUN
ajst-2984	19	84	of	of	ADP
ajst-2984	19	85	unhealthy	unhealthy	ADJ
ajst-2984	19	86	class	class	NOUN
ajst-2984	19	87	characteristic	characteristic	ADJ
ajst-2984	19	88	vector	vector	NOUN
ajst-2984	19	89	word	word	NOUN
ajst-2984	19	90	can	can	AUX
ajst-2984	19	91	be	be	AUX
ajst-2984	19	92	obtained	obtain	VERB
ajst-2984	19	93	using	use	VERB
ajst-2984	19	94	the	the	DET
ajst-2984	19	95	following	follow	VERB
ajst-2984	19	96	query	query	NOUN
ajst-2984	19	97	statements	statement	NOUN
ajst-2984	19	98	:	:	PUNCT
ajst-2984	19	99	select	select	VERB
ajst-2984	19	100	top	top	ADJ
ajst-2984	19	101	350	350	NUM
ajst-2984	19	102	a.word	a.word	NOUN
ajst-2984	19	103	,	,	PUNCT
ajst-2984	19	104	(	(	PUNCT
ajst-2984	19	105	a.frequence-b.frequence	a.frequence-b.frequence	NOUN
ajst-2984	19	106	)	)	PUNCT
ajst-2984	19	107	as	as	ADP
ajst-2984	19	108	frequency	frequency	NOUN
ajst-2984	19	109	difference	difference	NOUN
ajst-2984	19	110	.	.	PUNCT
ajst-2984	20	1	a.id	a.id	PROPN
ajst-2984	20	2	as	as	ADP
ajst-2984	20	3	‘	'	PUNCT
ajst-2984	20	4	[	[	X
ajst-2984	20	5	unhealthy	unhealthy	ADJ
ajst-2984	20	6	class	class	NOUN
ajst-2984	20	7	:	:	PUNCT
ajst-2984	20	8	i	i	PROPN
ajst-2984	20	9	d	d	PROPN
ajst-2984	20	10	’	'	PUNCT
ajst-2984	20	11	,	,	PUNCT
ajst-2984	20	12	a.rank	a.rank	VERB
ajst-2984	20	13	as	as	ADP
ajst-2984	20	14	rank	rank	NOUN
ajst-2984	20	15	,	,	PUNCT
ajst-2984	20	16	a.frequence	a.frequence	NOUN
ajst-2984	20	17	as	as	ADP
ajst-2984	20	18	frequence	frequence	NOUN
ajst-2984	20	19	,	,	PUNCT
ajst-2984	20	20	a.type	a.type	VERB
ajst-2984	20	21	as	as	ADP
ajst-2984	20	22	‘	'	PUNCT
ajst-2984	20	23	type	type	NOUN
ajst-2984	20	24	]	]	PUNCT
ajst-2984	20	25	’	'	PUNCT
ajst-2984	20	26	.	.	PUNCT
ajst-2984	21	1	b.id	b.id	PROPN
ajst-2984	21	2	as	as	ADP
ajst-2984	21	3	‘	'	PUNCT
ajst-2984	21	4	[	[	X
ajst-2984	21	5	common	common	ADJ
ajst-2984	21	6	class	class	NOUN
ajst-2984	21	7	:	:	PUNCT
ajst-2984	21	8	i	i	PROPN
ajst-2984	21	9	d	d	PROPN
ajst-2984	21	10	’	'	PUNCT
ajst-2984	21	11	,	,	PUNCT
ajst-2984	21	12	a.rank	a.rank	VERB
ajst-2984	21	13	as	as	ADP
ajst-2984	21	14	rank	rank	NOUN
ajst-2984	21	15	,	,	PUNCT
ajst-2984	21	16	a.frequence	a.frequence	NOUN
ajst-2984	21	17	as	as	ADP
ajst-2984	21	18	frequence	frequence	NOUN
ajst-2984	21	19	,	,	PUNCT
ajst-2984	21	20	a.type	a.type	VERB
ajst-2984	21	21	as	as	ADP
ajst-2984	21	22	‘	'	PUNCT
ajst-2984	21	23	type	type	NOUN
ajst-2984	21	24	]	]	PUNCT
ajst-2984	21	25	’	'	PUNCT
ajst-2984	21	26	.	.	PUNCT
ajst-2984	22	1	from	from	ADP
ajst-2984	22	2	(	(	PUNCT
ajst-2984	22	3	select	select	VERB
ajst-2984	22	4	*	*	PUNCT
ajst-2984	22	5	from	from	ADP
ajst-2984	22	6	docsetfrq	docsetfrq	ADJ
ajst-2984	22	7	where	where	SCONJ
ajst-2984	22	8	word	word	NOUN
ajst-2984	22	9	not	not	PART
ajst-2984	22	10	in	in	ADP
ajst-2984	22	11	(	(	PUNCT
ajst-2984	22	12	select	select	ADJ
ajst-2984	22	13	word	word	NOUN
ajst-2984	22	14	from	from	ADP
ajst-2984	22	15	st_stopword))as	st_stopword))as	PROPN
ajst-2984	22	16	a	a	PRON
ajst-2984	22	17	,	,	PUNCT
ajst-2984	22	18	docsetfrq	docsetfrq	ADJ
ajst-2984	22	19	as	as	ADP
ajst-2984	22	20	b	b	NUM
ajst-2984	22	21	where	where	SCONJ
ajst-2984	22	22	(	(	PUNCT
ajst-2984	22	23	a.type=1	a.type=1	NOUN
ajst-2984	22	24	and	and	CCONJ
ajst-2984	22	25	b.type=0	b.type=0	PUNCT
ajst-2984	22	26	and	and	CCONJ
ajst-2984	22	27	a.word	a.word	NOUN
ajst-2984	22	28	=	=	NOUN
ajst-2984	22	29	b.word	b.word	NOUN
ajst-2984	22	30	and	and	CCONJ
ajst-2984	22	31	(	(	PUNCT
ajst-2984	22	32	a.frequence	a.frequence	NOUN
ajst-2984	22	33	-	-	PUNCT
ajst-2984	22	34	b.frequence)>0.02	b.frequence)>0.02	NOUN
ajst-2984	22	35	)	)	PUNCT
ajst-2984	22	36	order	order	NOUN
ajst-2984	22	37	by	by	ADP
ajst-2984	22	38	(	(	PUNCT
ajst-2984	22	39	a.frequence-b.frequence	a.frequence-b.frequence	NOUN
ajst-2984	22	40	)	)	PUNCT
ajst-2984	22	41	desc	desc	NOUN
ajst-2984	22	42	note	note	NOUN
ajst-2984	22	43	:	:	PUNCT
ajst-2984	22	44	the	the	DET
ajst-2984	22	45	above	above	ADJ
ajst-2984	22	46	thresholds	threshold	NOUN
ajst-2984	22	47	can	can	AUX
ajst-2984	22	48	be	be	AUX
ajst-2984	22	49	adjusted	adjust	VERB
ajst-2984	22	50	according	accord	VERB
ajst-2984	22	51	to	to	ADP
ajst-2984	22	52	actual	actual	ADJ
ajst-2984	22	53	needs	need	NOUN
ajst-2984	22	54	.	.	PUNCT
ajst-2984	23	1	in	in	ADP
ajst-2984	23	2	the	the	DET
ajst-2984	23	3	above	above	ADJ
ajst-2984	23	4	statements	statement	NOUN
ajst-2984	23	5	,	,	PUNCT
ajst-2984	23	6	a.type=1	a.type=1	PUNCT
ajst-2984	23	7	and	and	CCONJ
ajst-2984	23	8	(	(	PUNCT
ajst-2984	23	9	a.frequence	a.frequence	NOUN
ajst-2984	23	10	-	-	PUNCT
ajst-2984	23	11	b.frequence)>0.02	b.frequence)>0.02	NOUN
ajst-2984	23	12	ensures	ensure	VERB
ajst-2984	23	13	that	that	SCONJ
ajst-2984	23	14	the	the	DET
ajst-2984	23	15	frequency	frequency	NOUN
ajst-2984	23	16	of	of	ADP
ajst-2984	23	17	type=1	type=1	PROPN
ajst-2984	23	18	is	be	AUX
ajst-2984	23	19	at	at	ADP
ajst-2984	23	20	least	least	ADJ
ajst-2984	23	21	above	above	ADP
ajst-2984	23	22	0.02	0.02	NUM
ajst-2984	23	23	,	,	PUNCT
ajst-2984	23	24	that	that	ADV
ajst-2984	23	25	is	is	ADV
ajst-2984	23	26	,	,	PUNCT
ajst-2984	23	27	a.frequence>0.02	a.frequence>0.02	PROPN
ajst-2984	23	28	.	.	PUNCT
ajst-2984	23	29	212	212	NUM
ajst-2984	23	30	4	4	NUM
ajst-2984	23	31	.	.	PUNCT
ajst-2984	23	32	creation	creation	NOUN
ajst-2984	23	33	of	of	ADP
ajst-2984	23	34	stop	stop	VERB
ajst-2984	23	35	vector	vector	NOUN
ajst-2984	23	36	word	word	NOUN
ajst-2984	23	37	if	if	SCONJ
ajst-2984	23	38	a	a	DET
ajst-2984	23	39	character	character	NOUN
ajst-2984	23	40	has	have	VERB
ajst-2984	23	41	a	a	DET
ajst-2984	23	42	large	large	ADJ
ajst-2984	23	43	frequency	frequency	NOUN
ajst-2984	23	44	value	value	NOUN
ajst-2984	23	45	in	in	ADP
ajst-2984	23	46	common	common	ADJ
ajst-2984	23	47	class	class	NOUN
ajst-2984	23	48	characteristic	characteristic	ADJ
ajst-2984	23	49	vector	vector	NOUN
ajst-2984	23	50	library	library	NOUN
ajst-2984	23	51	and	and	CCONJ
ajst-2984	23	52	unhealthy	unhealthy	ADJ
ajst-2984	23	53	class	class	NOUN
ajst-2984	23	54	characteristic	characteristic	ADJ
ajst-2984	23	55	vector	vector	NOUN
ajst-2984	23	56	library	library	NOUN
ajst-2984	23	57	,	,	PUNCT
ajst-2984	23	58	and	and	CCONJ
ajst-2984	23	59	both	both	PRON
ajst-2984	23	60	rank	rank	VERB
ajst-2984	23	61	relatively	relatively	ADV
ajst-2984	23	62	high	high	ADJ
ajst-2984	23	63	,	,	PUNCT
ajst-2984	23	64	it	it	PRON
ajst-2984	23	65	is	be	AUX
ajst-2984	23	66	considered	consider	VERB
ajst-2984	23	67	that	that	SCONJ
ajst-2984	23	68	the	the	DET
ajst-2984	23	69	classification	classification	NOUN
ajst-2984	23	70	tendency	tendency	NOUN
ajst-2984	23	71	is	be	AUX
ajst-2984	23	72	very	very	ADV
ajst-2984	23	73	weak	weak	ADJ
ajst-2984	23	74	.	.	PUNCT
ajst-2984	24	1	if	if	SCONJ
ajst-2984	24	2	it	it	PRON
ajst-2984	24	3	often	often	ADV
ajst-2984	24	4	appears	appear	VERB
ajst-2984	24	5	in	in	ADP
ajst-2984	24	6	the	the	DET
ajst-2984	24	7	document	document	NOUN
ajst-2984	24	8	set	set	NOUN
ajst-2984	24	9	.	.	PUNCT
ajst-2984	25	1	after	after	ADP
ajst-2984	25	2	removing	remove	VERB
ajst-2984	25	3	the	the	DET
ajst-2984	25	4	character	character	NOUN
ajst-2984	25	5	,	,	PUNCT
ajst-2984	25	6	it	it	PRON
ajst-2984	25	7	does	do	AUX
ajst-2984	25	8	not	not	PART
ajst-2984	25	9	affect	affect	VERB
ajst-2984	25	10	the	the	DET
ajst-2984	25	11	theme	theme	NOUN
ajst-2984	25	12	analysis	analysis	NOUN
ajst-2984	25	13	of	of	ADP
ajst-2984	25	14	the	the	DET
ajst-2984	25	15	text	text	NOUN
ajst-2984	25	16	,	,	PUNCT
ajst-2984	25	17	and	and	CCONJ
ajst-2984	25	18	this	this	DET
ajst-2984	25	19	kind	kind	NOUN
ajst-2984	25	20	of	of	ADP
ajst-2984	25	21	vector	vector	NOUN
ajst-2984	25	22	word	word	NOUN
ajst-2984	25	23	is	be	AUX
ajst-2984	25	24	called	call	VERB
ajst-2984	25	25	stop	stop	VERB
ajst-2984	25	26	vector	vector	NOUN
ajst-2984	25	27	word	word	NOUN
ajst-2984	25	28	.	.	PUNCT
ajst-2984	26	1	the	the	DET
ajst-2984	26	2	construction	construction	NOUN
ajst-2984	26	3	of	of	ADP
ajst-2984	26	4	stop	stop	VERB
ajst-2984	26	5	vector	vector	NOUN
ajst-2984	26	6	word	word	NOUN
ajst-2984	26	7	library	library	NOUN
ajst-2984	26	8	has	have	VERB
ajst-2984	26	9	a	a	DET
ajst-2984	26	10	premise	premise	NOUN
ajst-2984	26	11	:	:	PUNCT
ajst-2984	26	12	given	give	VERB
ajst-2984	26	13	a	a	DET
ajst-2984	26	14	sufficient	sufficient	ADJ
ajst-2984	26	15	amount	amount	NOUN
ajst-2984	26	16	of	of	ADP
ajst-2984	26	17	training	training	NOUN
ajst-2984	26	18	document	document	NOUN
ajst-2984	26	19	set	set	NOUN
ajst-2984	26	20	,	,	PUNCT
ajst-2984	26	21	build	build	VERB
ajst-2984	26	22	common	common	ADJ
ajst-2984	26	23	class	class	NOUN
ajst-2984	26	24	characteristic	characteristic	ADJ
ajst-2984	26	25	vector	vector	NOUN
ajst-2984	26	26	library	library	NOUN
ajst-2984	26	27	and	and	CCONJ
ajst-2984	26	28	unhealthy	unhealthy	ADJ
ajst-2984	26	29	class	class	NOUN
ajst-2984	26	30	characteristic	characteristic	ADJ
ajst-2984	26	31	vector	vector	NOUN
ajst-2984	26	32	library	library	NOUN
ajst-2984	26	33	.	.	PUNCT
ajst-2984	27	1	steps	step	NOUN
ajst-2984	27	2	of	of	ADP
ajst-2984	27	3	create	create	VERB
ajst-2984	27	4	library	library	NOUN
ajst-2984	27	5	of	of	ADP
ajst-2984	27	6	stop	stop	VERB
ajst-2984	27	7	vector	vector	NOUN
ajst-2984	27	8	word	word	NOUN
ajst-2984	27	9	:	:	PUNCT
ajst-2984	27	10	1)common	1)common	NUM
ajst-2984	27	11	class	class	NOUN
ajst-2984	27	12	characteristic	characteristic	ADJ
ajst-2984	27	13	vector	vector	NOUN
ajst-2984	27	14	library	library	NOUN
ajst-2984	27	15	is	be	AUX
ajst-2984	27	16	generated	generate	VERB
ajst-2984	27	17	by	by	ADP
ajst-2984	27	18	the	the	DET
ajst-2984	27	19	common	common	ADJ
ajst-2984	27	20	class	class	NOUN
ajst-2984	27	21	adaptive	adaptive	ADJ
ajst-2984	27	22	training	training	NOUN
ajst-2984	27	23	sample	sample	NOUN
ajst-2984	27	24	library	library	NOUN
ajst-2984	27	25	;	;	PUNCT
ajst-2984	27	26	2)unhealthy	2)unhealthy	NUM
ajst-2984	27	27	class	class	NOUN
ajst-2984	27	28	characteristic	characteristic	ADJ
ajst-2984	27	29	vector	vector	NOUN
ajst-2984	27	30	library	library	NOUN
ajst-2984	27	31	is	be	AUX
ajst-2984	27	32	generated	generate	VERB
ajst-2984	27	33	by	by	ADP
ajst-2984	27	34	the	the	DET
ajst-2984	27	35	unhealthy	unhealthy	ADJ
ajst-2984	27	36	class	class	NOUN
ajst-2984	27	37	adaptive	adaptive	ADJ
ajst-2984	27	38	training	training	NOUN
ajst-2984	27	39	sample	sample	NOUN
ajst-2984	27	40	library	library	NOUN
ajst-2984	27	41	;	;	PUNCT
ajst-2984	27	42	3)using	3)use	VERB
ajst-2984	27	43	the	the	DET
ajst-2984	27	44	rule	rule	NOUN
ajst-2984	27	45	of	of	ADP
ajst-2984	27	46	stop	stop	VERB
ajst-2984	27	47	vector	vector	NOUN
ajst-2984	27	48	word	word	NOUN
ajst-2984	27	49	and	and	CCONJ
ajst-2984	27	50	comparing	compare	VERB
ajst-2984	27	51	the	the	DET
ajst-2984	27	52	unhealthy	unhealthy	ADJ
ajst-2984	27	53	class	class	NOUN
ajst-2984	27	54	characteristic	characteristic	ADJ
ajst-2984	27	55	vector	vector	NOUN
ajst-2984	27	56	library	library	NOUN
ajst-2984	27	57	,	,	PUNCT
ajst-2984	27	58	plus	plus	CCONJ
ajst-2984	27	59	manual	manual	ADJ
ajst-2984	27	60	judgment	judgment	NOUN
ajst-2984	27	61	,	,	PUNCT
ajst-2984	27	62	library	library	NOUN
ajst-2984	27	63	of	of	ADP
ajst-2984	27	64	stop	stop	VERB
ajst-2984	27	65	vector	vector	NOUN
ajst-2984	27	66	word	word	NOUN
ajst-2984	27	67	is	be	AUX
ajst-2984	27	68	generated	generate	VERB
ajst-2984	27	69	.	.	PUNCT
ajst-2984	28	1	this	this	DET
ajst-2984	28	2	kind	kind	NOUN
ajst-2984	28	3	of	of	ADP
ajst-2984	28	4	stop	stop	VERB
ajst-2984	28	5	vector	vector	NOUN
ajst-2984	28	6	word	word	NOUN
ajst-2984	28	7	is	be	AUX
ajst-2984	28	8	generally	generally	ADV
ajst-2984	28	9	small	small	ADJ
ajst-2984	28	10	,	,	PUNCT
ajst-2984	28	11	generally	generally	ADV
ajst-2984	28	12	called	call	VERB
ajst-2984	28	13	library	library	NOUN
ajst-2984	28	14	of	of	ADP
ajst-2984	28	15	stop	stop	VERB
ajst-2984	28	16	vector	vector	NOUN
ajst-2984	28	17	word	word	NOUN
ajst-2984	28	18	.	.	PUNCT
ajst-2984	29	1	based	base	VERB
ajst-2984	29	2	on	on	ADP
ajst-2984	29	3	both	both	PRON
ajst-2984	29	4	of	of	ADP
ajst-2984	29	5	characteristic	characteristic	ADJ
ajst-2984	29	6	vector	vector	NOUN
ajst-2984	29	7	ranking	ranking	NOUN
ajst-2984	29	8	and	and	CCONJ
ajst-2984	29	9	word	word	NOUN
ajst-2984	29	10	frequency	frequency	NOUN
ajst-2984	29	11	two	two	NUM
ajst-2984	29	12	fields	field	NOUN
ajst-2984	29	13	,	,	PUNCT
ajst-2984	29	14	set	set	VERB
ajst-2984	29	15	a	a	DET
ajst-2984	29	16	threshold	threshold	NOUN
ajst-2984	29	17	,	,	PUNCT
ajst-2984	29	18	and	and	CCONJ
ajst-2984	29	19	build	build	VERB
ajst-2984	29	20	a	a	DET
ajst-2984	29	21	rough	rough	ADJ
ajst-2984	29	22	library	library	NOUN
ajst-2984	29	23	of	of	ADP
ajst-2984	29	24	stop	stop	VERB
ajst-2984	29	25	vector	vector	NOUN
ajst-2984	29	26	word	word	NOUN
ajst-2984	29	27	,	,	PUNCT
ajst-2984	29	28	for	for	ADP
ajst-2984	29	29	example	example	NOUN
ajst-2984	29	30	:	:	PUNCT
ajst-2984	29	31	we	we	PRON
ajst-2984	29	32	can	can	AUX
ajst-2984	29	33	use	use	VERB
ajst-2984	29	34	the	the	DET
ajst-2984	29	35	following	follow	VERB
ajst-2984	29	36	query	query	NOUN
ajst-2984	29	37	to	to	PART
ajst-2984	29	38	obtain	obtain	VERB
ajst-2984	29	39	stop	stop	VERB
ajst-2984	29	40	vector	vector	NOUN
ajst-2984	29	41	word	word	NOUN
ajst-2984	29	42	from	from	ADP
ajst-2984	29	43	the	the	DET
ajst-2984	29	44	common	common	ADJ
ajst-2984	29	45	class	class	NOUN
ajst-2984	29	46	characteristic	characteristic	ADJ
ajst-2984	29	47	vector	vector	NOUN
ajst-2984	29	48	library	library	NOUN
ajst-2984	29	49	“	"	PUNCT
ajst-2984	29	50	docsetfrq	docsetfrq	PROPN
ajst-2984	29	51	”	"	PUNCT
ajst-2984	29	52	:	:	PUNCT
ajst-2984	29	53	select	select	VERB
ajst-2984	29	54	top	top	ADJ
ajst-2984	29	55	100	100	NUM
ajst-2984	29	56	*	*	PUNCT
ajst-2984	29	57	from	from	ADP
ajst-2984	29	58	docsetfrq	docsetfrq	PROPN
ajst-2984	29	59	d	d	PROPN
ajst-2984	29	60	where	where	SCONJ
ajst-2984	29	61	(	(	PUNCT
ajst-2984	29	62	d.type=0	d.type=0	NOUN
ajst-2984	29	63	and	and	CCONJ
ajst-2984	29	64	d.rank<100	d.rank<100	PROPN
ajst-2984	29	65	and	and	CCONJ
ajst-2984	29	66	d.frequence>0.2	d.frequence>0.2	PROPN
ajst-2984	29	67	)	)	PUNCT
ajst-2984	29	68	order	order	NOUN
ajst-2984	29	69	by	by	ADP
ajst-2984	29	70	d.rank	d.rank	NOUN
ajst-2984	29	71	5	5	NUM
ajst-2984	29	72	.	.	PUNCT
ajst-2984	30	1	two	two	NUM
ajst-2984	30	2	rules	rule	NOUN
ajst-2984	30	3	obtained	obtain	VERB
ajst-2984	30	4	from	from	ADP
ajst-2984	30	5	experimental	experimental	ADJ
ajst-2984	30	6	rule	rule	NOUN
ajst-2984	30	7	1(rule	1(rule	NUM
ajst-2984	30	8	of	of	ADP
ajst-2984	30	9	stop	stop	VERB
ajst-2984	30	10	vector	vector	NOUN
ajst-2984	30	11	word	word	NOUN
ajst-2984	30	12	):	):	PUNCT
ajst-2984	30	13	after	after	ADP
ajst-2984	30	14	constructing	construct	VERB
ajst-2984	30	15	the	the	DET
ajst-2984	30	16	common	common	ADJ
ajst-2984	30	17	class	class	NOUN
ajst-2984	30	18	characteristic	characteristic	ADJ
ajst-2984	30	19	vector	vector	NOUN
ajst-2984	30	20	library	library	NOUN
ajst-2984	30	21	,	,	PUNCT
ajst-2984	30	22	according	accord	VERB
ajst-2984	30	23	to	to	ADP
ajst-2984	30	24	the	the	DET
ajst-2984	30	25	word	word	NOUN
ajst-2984	30	26	frequency	frequency	NOUN
ajst-2984	30	27	ranking	ranking	NOUN
ajst-2984	30	28	of	of	ADP
ajst-2984	30	29	the	the	DET
ajst-2984	30	30	characteristic	characteristic	ADJ
ajst-2984	30	31	vector	vector	NOUN
ajst-2984	30	32	,	,	PUNCT
ajst-2984	30	33	the	the	DET
ajst-2984	30	34	topranked	topranke	VERB
ajst-2984	30	35	feature	feature	NOUN
ajst-2984	30	36	vectors	vector	NOUN
ajst-2984	30	37	are	be	AUX
ajst-2984	30	38	generally	generally	ADV
ajst-2984	30	39	meaningless	meaningless	ADJ
ajst-2984	30	40	,	,	PUNCT
ajst-2984	30	41	and	and	CCONJ
ajst-2984	30	42	the	the	DET
ajst-2984	30	43	elimination	elimination	NOUN
ajst-2984	30	44	of	of	ADP
ajst-2984	30	45	such	such	ADJ
ajst-2984	30	46	characteristic	characteristic	ADJ
ajst-2984	30	47	vectors	vector	NOUN
ajst-2984	30	48	does	do	AUX
ajst-2984	30	49	not	not	PART
ajst-2984	30	50	affect	affect	VERB
ajst-2984	30	51	the	the	DET
ajst-2984	30	52	theme	theme	NOUN
ajst-2984	30	53	of	of	ADP
ajst-2984	30	54	the	the	DET
ajst-2984	30	55	document	document	NOUN
ajst-2984	30	56	.	.	PUNCT
ajst-2984	31	1	therefore	therefore	ADV
ajst-2984	31	2	,	,	PUNCT
ajst-2984	31	3	such	such	ADJ
ajst-2984	31	4	characteristic	characteristic	ADJ
ajst-2984	31	5	vectors	vector	NOUN
ajst-2984	31	6	can	can	AUX
ajst-2984	31	7	be	be	AUX
ajst-2984	31	8	used	use	VERB
ajst-2984	31	9	as	as	SCONJ
ajst-2984	31	10	stop	stop	VERB
ajst-2984	31	11	vector	vector	NOUN
ajst-2984	31	12	word	word	NOUN
ajst-2984	31	13	.	.	PUNCT
ajst-2984	32	1	in	in	ADP
ajst-2984	32	2	the	the	DET
ajst-2984	32	3	actual	actual	ADJ
ajst-2984	32	4	construction	construction	NOUN
ajst-2984	32	5	of	of	ADP
ajst-2984	32	6	rule	rule	NOUN
ajst-2984	32	7	of	of	ADP
ajst-2984	32	8	stop	stop	NOUN
ajst-2984	32	9	vector	vector	NOUN
ajst-2984	32	10	word	word	NOUN
ajst-2984	32	11	,	,	PUNCT
ajst-2984	32	12	it	it	PRON
ajst-2984	32	13	is	be	AUX
ajst-2984	32	14	also	also	ADV
ajst-2984	32	15	necessary	necessary	ADJ
ajst-2984	32	16	to	to	PART
ajst-2984	32	17	determine	determine	VERB
ajst-2984	32	18	an	an	DET
ajst-2984	32	19	appropriate	appropriate	ADJ
ajst-2984	32	20	size	size	NOUN
ajst-2984	32	21	of	of	ADP
ajst-2984	32	22	stop	stop	VERB
ajst-2984	32	23	vector	vector	NOUN
ajst-2984	32	24	word	word	NOUN
ajst-2984	32	25	based	base	VERB
ajst-2984	32	26	on	on	ADP
ajst-2984	32	27	the	the	DET
ajst-2984	32	28	experience	experience	NOUN
ajst-2984	32	29	of	of	ADP
ajst-2984	32	30	rule	rule	NOUN
ajst-2984	32	31	of	of	ADP
ajst-2984	32	32	stop	stop	NOUN
ajst-2984	32	33	vector	vector	NOUN
ajst-2984	32	34	word	word	NOUN
ajst-2984	32	35	.	.	PUNCT
ajst-2984	33	1	rule	rule	VERB
ajst-2984	33	2	2(rule	2(rule	NUM
ajst-2984	33	3	of	of	ADP
ajst-2984	33	4	feature	feature	NOUN
ajst-2984	33	5	word	word	NOUN
ajst-2984	33	6	):	):	PUNCT
ajst-2984	33	7	the	the	DET
ajst-2984	33	8	corresponding	corresponding	ADJ
ajst-2984	33	9	word	word	NOUN
ajst-2984	33	10	frequency	frequency	NOUN
ajst-2984	33	11	of	of	ADP
ajst-2984	33	12	the	the	DET
ajst-2984	33	13	same	same	ADJ
ajst-2984	33	14	character	character	NOUN
ajst-2984	33	15	in	in	ADP
ajst-2984	33	16	common	common	ADJ
ajst-2984	33	17	class	class	NOUN
ajst-2984	33	18	training	training	NOUN
ajst-2984	33	19	corpus	corpus	NOUN
ajst-2984	33	20	and	and	CCONJ
ajst-2984	33	21	unhealty	unhealty	ADJ
ajst-2984	33	22	class	class	NOUN
ajst-2984	33	23	training	training	NOUN
ajst-2984	33	24	corpus	corpus	NOUN
ajst-2984	33	25	is	be	AUX
ajst-2984	33	26	usually	usually	ADV
ajst-2984	33	27	different	different	ADJ
ajst-2984	33	28	.	.	PUNCT
ajst-2984	34	1	if	if	SCONJ
ajst-2984	34	2	the	the	DET
ajst-2984	34	3	absolute	absolute	ADJ
ajst-2984	34	4	value	value	NOUN
ajst-2984	34	5	of	of	ADP
ajst-2984	34	6	the	the	DET
ajst-2984	34	7	word	word	NOUN
ajst-2984	34	8	frequency	frequency	NOUN
ajst-2984	34	9	difference	difference	NOUN
ajst-2984	34	10	of	of	ADP
ajst-2984	34	11	the	the	DET
ajst-2984	34	12	same	same	ADJ
ajst-2984	34	13	character	character	NOUN
ajst-2984	34	14	in	in	ADP
ajst-2984	34	15	common	common	ADJ
ajst-2984	34	16	class	class	NOUN
ajst-2984	34	17	characteristic	characteristic	ADJ
ajst-2984	34	18	vector	vector	NOUN
ajst-2984	34	19	library	library	NOUN
ajst-2984	34	20	and	and	CCONJ
ajst-2984	34	21	unhealty	unhealty	ADJ
ajst-2984	34	22	class	class	NOUN
ajst-2984	34	23	characteristic	characteristic	ADJ
ajst-2984	34	24	vector	vector	NOUN
ajst-2984	34	25	library	library	NOUN
ajst-2984	34	26	is	be	AUX
ajst-2984	34	27	sorted	sort	VERB
ajst-2984	34	28	,	,	PUNCT
ajst-2984	34	29	the	the	PRON
ajst-2984	34	30	larger	large	ADJ
ajst-2984	34	31	the	the	DET
ajst-2984	34	32	difference	difference	NOUN
ajst-2984	34	33	,	,	PUNCT
ajst-2984	34	34	the	the	PRON
ajst-2984	34	35	greater	great	ADJ
ajst-2984	34	36	the	the	DET
ajst-2984	34	37	tendency	tendency	NOUN
ajst-2984	34	38	of	of	ADP
ajst-2984	34	39	the	the	DET
ajst-2984	34	40	unhealty	unhealty	ADJ
ajst-2984	34	41	class	class	NOUN
ajst-2984	34	42	category	category	NOUN
ajst-2984	34	43	,	,	PUNCT
ajst-2984	34	44	indicating	indicate	VERB
ajst-2984	34	45	that	that	SCONJ
ajst-2984	34	46	the	the	PRON
ajst-2984	34	47	higher	high	ADJ
ajst-2984	34	48	the	the	DET
ajst-2984	34	49	feature	feature	NOUN
ajst-2984	34	50	strength	strength	NOUN
ajst-2984	34	51	of	of	ADP
ajst-2984	34	52	the	the	DET
ajst-2984	34	53	word	word	NOUN
ajst-2984	34	54	,	,	PUNCT
ajst-2984	34	55	it	it	PRON
ajst-2984	34	56	can	can	AUX
ajst-2984	34	57	be	be	AUX
ajst-2984	34	58	called	call	VERB
ajst-2984	34	59	"	"	PUNCT
ajst-2984	34	60	unhealty	unhealty	ADJ
ajst-2984	34	61	class	class	NOUN
ajst-2984	34	62	characteristic	characteristic	ADJ
ajst-2984	34	63	vector	vector	NOUN
ajst-2984	34	64	word	word	NOUN
ajst-2984	34	65	"	"	PUNCT
ajst-2984	34	66	.	.	PUNCT
ajst-2984	35	1	6	6	X
ajst-2984	35	2	.	.	X
ajst-2984	35	3	construction	construction	NOUN
ajst-2984	35	4	and	and	CCONJ
ajst-2984	35	5	prediction	prediction	NOUN
ajst-2984	35	6	of	of	ADP
ajst-2984	35	7	unhealty	unhealty	ADJ
ajst-2984	35	8	category	category	NOUN
ajst-2984	35	9	pattern	pattern	NOUN
ajst-2984	35	10	1	1	NUM
ajst-2984	35	11	)	)	PUNCT
ajst-2984	35	12	unhealty	unhealty	ADJ
ajst-2984	35	13	category	category	NOUN
ajst-2984	35	14	pattern	pattern	NOUN
ajst-2984	35	15	building	building	NOUN
ajst-2984	35	16	algorithm	algorithm	NOUN
ajst-2984	35	17	,	,	PUNCT
ajst-2984	35	18	the	the	DET
ajst-2984	35	19	steps	step	NOUN
ajst-2984	35	20	are	be	AUX
ajst-2984	35	21	as	as	SCONJ
ajst-2984	35	22	follows	follow	VERB
ajst-2984	35	23	:	:	PUNCT
ajst-2984	35	24	①	①	NUM
ajst-2984	35	25	using	use	VERB
ajst-2984	35	26	characteristic	characteristic	ADJ
ajst-2984	35	27	vector	vector	NOUN
ajst-2984	35	28	library	library	NOUN
ajst-2984	35	29	and	and	CCONJ
ajst-2984	35	30	generating	generate	VERB
ajst-2984	35	31	unhealthy	unhealthy	ADJ
ajst-2984	35	32	class	class	NOUN
ajst-2984	35	33	characteristic	characteristic	ADJ
ajst-2984	35	34	vector	vector	NOUN
ajst-2984	35	35	library	library	NOUN
ajst-2984	35	36	according	accord	VERB
ajst-2984	35	37	to	to	ADP
ajst-2984	35	38	the	the	DET
ajst-2984	35	39	rule	rule	NOUN
ajst-2984	35	40	of	of	ADP
ajst-2984	35	41	characteristic	characteristic	ADJ
ajst-2984	35	42	vector	vector	NOUN
ajst-2984	35	43	;	;	PUNCT
ajst-2984	35	44	②using	②use	VERB
ajst-2984	35	45	the	the	DET
ajst-2984	35	46	feature	feature	NOUN
ajst-2984	35	47	threshold	threshold	NOUN
ajst-2984	35	48	to	to	PART
ajst-2984	35	49	extract	extract	VERB
ajst-2984	35	50	the	the	DET
ajst-2984	35	51	first	first	ADJ
ajst-2984	35	52	several	several	ADJ
ajst-2984	35	53	characteristic	characteristic	ADJ
ajst-2984	35	54	vectors	vector	NOUN
ajst-2984	35	55	from	from	ADP
ajst-2984	35	56	the	the	DET
ajst-2984	35	57	unhealthy	unhealthy	ADJ
ajst-2984	35	58	class	class	NOUN
ajst-2984	35	59	characteristic	characteristic	ADJ
ajst-2984	35	60	vector	vector	NOUN
ajst-2984	35	61	library	library	NOUN
ajst-2984	35	62	as	as	ADP
ajst-2984	35	63	the	the	DET
ajst-2984	35	64	unhealthy	unhealthy	ADJ
ajst-2984	35	65	class	class	NOUN
ajst-2984	35	66	standard	standard	ADJ
ajst-2984	35	67	pattern	pattern	NOUN
ajst-2984	35	68	;	;	PUNCT
ajst-2984	35	69	methods	method	NOUN
ajst-2984	35	70	:	:	PUNCT
ajst-2984	35	71	the	the	DET
ajst-2984	35	72	feature	feature	NOUN
ajst-2984	35	73	threshold	threshold	NOUN
ajst-2984	35	74	is	be	AUX
ajst-2984	35	75	set	set	VERB
ajst-2984	35	76	(	(	PUNCT
ajst-2984	35	77	the	the	DET
ajst-2984	35	78	absolute	absolute	ADJ
ajst-2984	35	79	difference	difference	NOUN
ajst-2984	35	80	of	of	ADP
ajst-2984	35	81	word	word	NOUN
ajst-2984	35	82	frequency	frequency	NOUN
ajst-2984	35	83	is	be	AUX
ajst-2984	35	84	specified	specify	VERB
ajst-2984	35	85	for	for	ADP
ajst-2984	35	86	filtering	filtering	NOUN
ajst-2984	35	87	,	,	PUNCT
ajst-2984	35	88	which	which	PRON
ajst-2984	35	89	can	can	AUX
ajst-2984	35	90	be	be	AUX
ajst-2984	35	91	adjusted	adjust	VERB
ajst-2984	35	92	according	accord	VERB
ajst-2984	35	93	to	to	ADP
ajst-2984	35	94	efficiency	efficiency	NOUN
ajst-2984	35	95	and	and	CCONJ
ajst-2984	35	96	filtering	filtering	NOUN
ajst-2984	35	97	accuracy	accuracy	NOUN
ajst-2984	35	98	)	)	PUNCT
ajst-2984	35	99	.	.	PUNCT
ajst-2984	36	1	from	from	ADP
ajst-2984	36	2	the	the	DET
ajst-2984	36	3	unhealthy	unhealthy	ADJ
ajst-2984	36	4	class	class	NOUN
ajst-2984	36	5	characteristic	characteristic	ADJ
ajst-2984	36	6	vector	vector	NOUN
ajst-2984	36	7	library	library	NOUN
ajst-2984	36	8	,	,	PUNCT
ajst-2984	36	9	according	accord	VERB
ajst-2984	36	10	to	to	ADP
ajst-2984	36	11	the	the	DET
ajst-2984	36	12	absolute	absolute	ADJ
ajst-2984	36	13	difference	difference	NOUN
ajst-2984	36	14	of	of	ADP
ajst-2984	36	15	word	word	NOUN
ajst-2984	36	16	frequency	frequency	NOUN
ajst-2984	36	17	,	,	PUNCT
ajst-2984	36	18	it	it	PRON
ajst-2984	36	19	is	be	AUX
ajst-2984	36	20	compared	compare	VERB
ajst-2984	36	21	with	with	ADP
ajst-2984	36	22	the	the	DET
ajst-2984	36	23	given	give	VERB
ajst-2984	36	24	threshold	threshold	NOUN
ajst-2984	36	25	respectively	respectively	ADV
ajst-2984	36	26	.	.	PUNCT
ajst-2984	37	1	the	the	DET
ajst-2984	37	2	higher	high	ADJ
ajst-2984	37	3	is	be	AUX
ajst-2984	37	4	selected	select	VERB
ajst-2984	37	5	and	and	CCONJ
ajst-2984	37	6	the	the	DET
ajst-2984	37	7	lower	low	ADJ
ajst-2984	37	8	is	be	AUX
ajst-2984	37	9	eliminated	eliminate	VERB
ajst-2984	37	10	.	.	PUNCT
ajst-2984	38	1	finally	finally	ADV
ajst-2984	38	2	,	,	PUNCT
ajst-2984	38	3	a	a	DET
ajst-2984	38	4	set	set	NOUN
ajst-2984	38	5	of	of	ADP
ajst-2984	38	6	unhealthy	unhealthy	ADJ
ajst-2984	38	7	class	class	NOUN
ajst-2984	38	8	characteristic	characteristic	ADJ
ajst-2984	38	9	vector	vector	NOUN
ajst-2984	38	10	word	word	NOUN
ajst-2984	38	11	which	which	PRON
ajst-2984	38	12	meet	meet	VERB
ajst-2984	38	13	the	the	DET
ajst-2984	38	14	requirements	requirement	NOUN
ajst-2984	38	15	can	can	AUX
ajst-2984	38	16	be	be	AUX
ajst-2984	38	17	obtained	obtain	VERB
ajst-2984	38	18	.	.	PUNCT
ajst-2984	39	1	after	after	ADP
ajst-2984	39	2	vectorizing	vectorize	VERB
ajst-2984	39	3	these	these	DET
ajst-2984	39	4	feature	feature	NOUN
ajst-2984	39	5	words	word	NOUN
ajst-2984	39	6	and	and	CCONJ
ajst-2984	39	7	their	their	PRON
ajst-2984	39	8	frequency	frequency	NOUN
ajst-2984	39	9	values	value	NOUN
ajst-2984	39	10	,	,	PUNCT
ajst-2984	39	11	"	"	PUNCT
ajst-2984	39	12	unhealty	unhealty	ADJ
ajst-2984	39	13	category	category	NOUN
ajst-2984	39	14	pattern	pattern	NOUN
ajst-2984	39	15	"	"	PUNCT
ajst-2984	39	16	is	be	AUX
ajst-2984	39	17	obtained	obtain	VERB
ajst-2984	39	18	.	.	PUNCT
ajst-2984	40	1	2)unhealthy	2)unhealthy	NUM
ajst-2984	40	2	category	category	NOUN
ajst-2984	40	3	pattern	pattern	NOUN
ajst-2984	40	4	filtering	filter	VERB
ajst-2984	40	5	algorithm	algorithm	NOUN
ajst-2984	40	6	,	,	PUNCT
ajst-2984	40	7	the	the	DET
ajst-2984	40	8	steps	step	NOUN
ajst-2984	40	9	are	be	AUX
ajst-2984	40	10	as	as	SCONJ
ajst-2984	40	11	follows	follow	VERB
ajst-2984	40	12	:	:	PUNCT
ajst-2984	40	13	①construct	①construct	VERB
ajst-2984	40	14	the	the	DET
ajst-2984	40	15	characteristic	characteristic	ADJ
ajst-2984	40	16	vector	vector	NOUN
ajst-2984	40	17	of	of	ADP
ajst-2984	40	18	the	the	DET
ajst-2984	40	19	test	test	NOUN
ajst-2984	40	20	document	document	NOUN
ajst-2984	40	21	;	;	PUNCT
ajst-2984	40	22	the	the	DET
ajst-2984	40	23	text	text	NOUN
ajst-2984	40	24	content	content	NOUN
ajst-2984	40	25	of	of	ADP
ajst-2984	40	26	the	the	DET
ajst-2984	40	27	webpage	webpage	NOUN
ajst-2984	40	28	is	be	AUX
ajst-2984	40	29	extracted	extract	VERB
ajst-2984	40	30	from	from	ADP
ajst-2984	40	31	the	the	DET
ajst-2984	40	32	test	test	NOUN
ajst-2984	40	33	document	document	NOUN
ajst-2984	40	34	,	,	PUNCT
ajst-2984	40	35	then	then	ADV
ajst-2984	40	36	the	the	DET
ajst-2984	40	37	word	word	NOUN
ajst-2984	40	38	frequency	frequency	NOUN
ajst-2984	40	39	of	of	ADP
ajst-2984	40	40	the	the	DET
ajst-2984	40	41	unhealthy	unhealthy	ADJ
ajst-2984	40	42	category	category	NOUN
ajst-2984	40	43	characteristic	characteristic	ADJ
ajst-2984	40	44	words	word	NOUN
ajst-2984	40	45	appearing	appear	VERB
ajst-2984	40	46	in	in	ADP
ajst-2984	40	47	the	the	DET
ajst-2984	40	48	document	document	NOUN
ajst-2984	40	49	is	be	AUX
ajst-2984	40	50	counted	count	VERB
ajst-2984	40	51	,	,	PUNCT
ajst-2984	40	52	and	and	CCONJ
ajst-2984	40	53	a	a	DET
ajst-2984	40	54	multidimensional	multidimensional	ADJ
ajst-2984	40	55	characteristic	characteristic	ADJ
ajst-2984	40	56	vector	vector	NOUN
ajst-2984	40	57	is	be	AUX
ajst-2984	40	58	constructed	construct	VERB
ajst-2984	40	59	with	with	ADP
ajst-2984	40	60	these	these	DET
ajst-2984	40	61	characters	character	NOUN
ajst-2984	40	62	and	and	CCONJ
ajst-2984	40	63	their	their	PRON
ajst-2984	40	64	word	word	NOUN
ajst-2984	40	65	frequency	frequency	NOUN
ajst-2984	40	66	in	in	ADP
ajst-2984	40	67	the	the	DET
ajst-2984	40	68	document	document	NOUN
ajst-2984	40	69	.	.	PUNCT
ajst-2984	41	1	assumption	assumption	NOUN
ajst-2984	41	2	:	:	PUNCT
ajst-2984	42	1	d	d	X
ajst-2984	42	2	=	=	NOUN
ajst-2984	42	3	d(t1,w1;t2,w2;	d(t1,w1;t2,w2;	NOUN
ajst-2984	42	4	.....	.....	PUNCT
ajst-2984	42	5	;tn	;tn	PROPN
ajst-2984	42	6	,	,	PUNCT
ajst-2984	42	7	wn	wn	PROPN
ajst-2984	42	8	)	)	PUNCT
ajst-2984	42	9	,	,	PUNCT
ajst-2984	42	10	where	where	SCONJ
ajst-2984	42	11	tk	tk	PROPN
ajst-2984	42	12	is	be	AUX
ajst-2984	42	13	the	the	DET
ajst-2984	42	14	feature	feature	NOUN
ajst-2984	42	15	character	character	NOUN
ajst-2984	42	16	term	term	NOUN
ajst-2984	42	17	,	,	PUNCT
ajst-2984	42	18	wk	wk	X
ajst-2984	42	19	is	be	AUX
ajst-2984	42	20	the	the	DET
ajst-2984	42	21	word	word	NOUN
ajst-2984	42	22	frequency	frequency	NOUN
ajst-2984	42	23	statistics	statistic	NOUN
ajst-2984	42	24	in	in	ADP
ajst-2984	42	25	the	the	DET
ajst-2984	42	26	test	test	NOUN
ajst-2984	42	27	document,1≤k≤n	document,1≤k≤n	NOUN
ajst-2984	42	28	.	.	PUNCT
ajst-2984	43	1	②compare	②compare	AUX
ajst-2984	43	2	test	test	NOUN
ajst-2984	43	3	document	document	NOUN
ajst-2984	43	4	characteristic	characteristic	ADJ
ajst-2984	43	5	vectors	vector	NOUN
ajst-2984	43	6	with	with	ADP
ajst-2984	43	7	unhealthy	unhealthy	ADJ
ajst-2984	43	8	category	category	NOUN
ajst-2984	43	9	patterns	pattern	NOUN
ajst-2984	43	10	,	,	PUNCT
ajst-2984	43	11	calculate	calculate	VERB
ajst-2984	43	12	the	the	DET
ajst-2984	43	13	similarity	similarity	NOUN
ajst-2984	43	14	,	,	PUNCT
ajst-2984	43	15	in	in	ADP
ajst-2984	43	16	order	order	NOUN
ajst-2984	43	17	to	to	PART
ajst-2984	43	18	filter	filter	VERB
ajst-2984	43	19	according	accord	VERB
ajst-2984	43	20	to	to	ADP
ajst-2984	43	21	the	the	DET
ajst-2984	43	22	threshold	threshold	NOUN
ajst-2984	43	23	.	.	PUNCT
ajst-2984	44	1	precondition	precondition	NOUN
ajst-2984	44	2	:	:	PUNCT
ajst-2984	44	3	suppose	suppose	VERB
ajst-2984	44	4	the	the	DET
ajst-2984	44	5	unhealthy	unhealthy	ADJ
ajst-2984	44	6	class	class	NOUN
ajst-2984	44	7	pattern	pattern	NOUN
ajst-2984	44	8	string	string	NOUN
ajst-2984	44	9	extracted	extract	VERB
ajst-2984	44	10	from	from	ADP
ajst-2984	44	11	the	the	DET
ajst-2984	44	12	database	database	NOUN
ajst-2984	44	13	is	be	AUX
ajst-2984	44	14	(	(	PUNCT
ajst-2984	44	15	a1,a2,	a1,a2,	PROPN
ajst-2984	44	16	...	...	PUNCT
ajst-2984	44	17	,an	,an	PUNCT
ajst-2984	44	18	)	)	PUNCT
ajst-2984	44	19	with	with	ADP
ajst-2984	44	20	frequencies	frequency	NOUN
ajst-2984	44	21	of	of	ADP
ajst-2984	44	22	(	(	PUNCT
ajst-2984	44	23	f1,f2,	f1,f2,	PROPN
ajst-2984	44	24	...	...	PUNCT
ajst-2984	44	25	,fn	,fn	PROPN
ajst-2984	44	26	)	)	PUNCT
ajst-2984	44	27	,	,	PUNCT
ajst-2984	44	28	their	their	PRON
ajst-2984	44	29	frequencies	frequency	NOUN
ajst-2984	44	30	in	in	ADP
ajst-2984	44	31	the	the	DET
ajst-2984	44	32	test	test	NOUN
ajst-2984	44	33	document	document	NOUN
ajst-2984	44	34	are	be	AUX
ajst-2984	44	35	(	(	PUNCT
ajst-2984	44	36	tf1,tf2,	tf1,tf2,	ADJ
ajst-2984	44	37	...	...	PUNCT
ajst-2984	44	38	,tfn	,tfn	PUNCT
ajst-2984	44	39	)	)	PUNCT
ajst-2984	44	40	.	.	PUNCT
ajst-2984	45	1	in	in	ADP
ajst-2984	45	2	this	this	DET
ajst-2984	45	3	paper	paper	NOUN
ajst-2984	45	4	,	,	PUNCT
ajst-2984	45	5	the	the	DET
ajst-2984	45	6	feature	feature	NOUN
ajst-2984	45	7	word	word	NOUN
ajst-2984	45	8	frequency	frequency	NOUN
ajst-2984	45	9	accumulation	accumulation	NOUN
ajst-2984	45	10	method	method	NOUN
ajst-2984	45	11	and	and	CCONJ
ajst-2984	45	12	cosine	cosine	NOUN
ajst-2984	45	13	metric	metric	ADJ
ajst-2984	45	14	method	method	NOUN
ajst-2984	45	15	are	be	AUX
ajst-2984	45	16	used	use	VERB
ajst-2984	45	17	to	to	PART
ajst-2984	45	18	calculate	calculate	VERB
ajst-2984	45	19	the	the	DET
ajst-2984	45	20	similarity	similarity	NOUN
ajst-2984	45	21	between	between	ADP
ajst-2984	45	22	unhealthy	unhealthy	ADJ
ajst-2984	45	23	category	category	NOUN
ajst-2984	45	24	pattern	pattern	NOUN
ajst-2984	45	25	and	and	CCONJ
ajst-2984	45	26	test	test	NOUN
ajst-2984	45	27	document	document	NOUN
ajst-2984	45	28	characteristic	characteristic	ADJ
ajst-2984	45	29	vector	vector	NOUN
ajst-2984	45	30	which	which	PRON
ajst-2984	45	31	are	be	AUX
ajst-2984	45	32	described	describe	VERB
ajst-2984	45	33	as	as	SCONJ
ajst-2984	45	34	follows	follow	VERB
ajst-2984	45	35	:	:	PUNCT
ajst-2984	45	36	①feature	①feature	NOUN
ajst-2984	45	37	word	word	NOUN
ajst-2984	45	38	frequency	frequency	NOUN
ajst-2984	45	39	accumulation	accumulation	NOUN
ajst-2984	45	40	:	:	PUNCT
ajst-2984	45	41	cumulative	cumulative	ADJ
ajst-2984	45	42	value	value	NOUN
ajst-2984	45	43	of	of	ADP
ajst-2984	45	44	each	each	DET
ajst-2984	45	45	character	character	NOUN
ajst-2984	45	46	in	in	ADP
ajst-2984	45	47	test	test	NOUN
ajst-2984	45	48	document	document	NOUN
ajst-2984	45	49	characteristic	characteristic	ADJ
ajst-2984	45	50	vector	vector	NOUN
ajst-2984	45	51	is	be	AUX
ajst-2984	45	52	called	call	VERB
ajst-2984	45	53	feature	feature	NOUN
ajst-2984	45	54	word	word	NOUN
ajst-2984	45	55	frequency	frequency	NOUN
ajst-2984	45	56	accumulation	accumulation	NOUN
ajst-2984	45	57	value	value	NOUN
ajst-2984	45	58	.	.	PUNCT
ajst-2984	46	1	unhealthy	unhealthy	ADJ
ajst-2984	46	2	category	category	NOUN
ajst-2984	46	3	mode	mode	NOUN
ajst-2984	46	4	character	character	NOUN
ajst-2984	46	5	frequency	frequency	NOUN
ajst-2984	46	6	cumulative	cumulative	ADJ
ajst-2984	46	7	value	value	NOUN
ajst-2984	46	8	:	:	PUNCT
ajst-2984	46	9	weight1	weight1	ADJ
ajst-2984	46	10	=	=	SYM
ajst-2984	46	11	f1+f2+	f1+f2+	X
ajst-2984	46	12	...	...	PUNCT
ajst-2984	46	13	+fn	+fn	ADJ
ajst-2984	46	14	;	;	PUNCT
ajst-2984	46	15	test	test	NOUN
ajst-2984	46	16	document	document	NOUN
ajst-2984	46	17	vector	vector	NOUN
ajst-2984	46	18	character	character	NOUN
ajst-2984	46	19	frequency	frequency	NOUN
ajst-2984	46	20	cumulative	cumulative	ADJ
ajst-2984	46	21	value	value	NOUN
ajst-2984	46	22	:	:	PUNCT
ajst-2984	46	23	weight2=	weight2=	VERB
ajst-2984	46	24	tf1+tf2+	tf1+tf2+	PROPN
ajst-2984	46	25	...	...	PUNCT
ajst-2984	46	26	+tfn	+tfn	NOUN
ajst-2984	46	27	;	;	PUNCT
ajst-2984	46	28	difference	difference	NOUN
ajst-2984	46	29	weight=|weight1	weight=|weight1	NOUN
ajst-2984	46	30	-	-	SYM
ajst-2984	46	31	weight2|	weight2|	NOUN
ajst-2984	46	32	;	;	PUNCT
ajst-2984	46	33	compare	compare	VERB
ajst-2984	46	34	weight	weight	NOUN
ajst-2984	46	35	with	with	ADP
ajst-2984	46	36	threshold	threshold	NOUN
ajst-2984	46	37	to	to	PART
ajst-2984	46	38	make	make	VERB
ajst-2984	46	39	predictions	prediction	NOUN
ajst-2984	46	40	or	or	CCONJ
ajst-2984	46	41	calculate	calculate	NOUN
ajst-2984	46	42	similarity	similarity	NOUN
ajst-2984	46	43	.	.	PUNCT
ajst-2984	47	1	②cosine	②cosine	PROPN
ajst-2984	47	2	metric	metric	NOUN
ajst-2984	47	3	:	:	PUNCT
ajst-2984	47	4	let	let	VERB
ajst-2984	47	5	v1	v1	VERB
ajst-2984	47	6	and	and	CCONJ
ajst-2984	47	7	v2	v2	PROPN
ajst-2984	47	8	represent	represent	VERB
ajst-2984	47	9	a	a	DET
ajst-2984	47	10	document	document	NOUN
ajst-2984	47	11	vector	vector	NOUN
ajst-2984	47	12	respectively	respectively	ADV
ajst-2984	47	13	,	,	PUNCT
ajst-2984	47	14	then	then	ADV
ajst-2984	47	15	the	the	DET
ajst-2984	47	16	similarity(cosine	similarity(cosine	PROPN
ajst-2984	47	17	metric	metric	NOUN
ajst-2984	47	18	)	)	PUNCT
ajst-2984	47	19	of	of	ADP
ajst-2984	47	20	the	the	DET
ajst-2984	47	21	two	two	NUM
ajst-2984	47	22	documents	document	NOUN
ajst-2984	47	23	is	be	AUX
ajst-2984	47	24	sim(v1,v2)=	sim(v1,v2)=	ADJ
ajst-2984	47	25	∙	∙	PROPN
ajst-2984	48	1	|	|	ADV
ajst-2984	48	2	||	||	ADV
ajst-2984	49	1	|	|	INTJ
ajst-2984	49	2	,	,	PUNCT
ajst-2984	49	3	where	where	SCONJ
ajst-2984	49	4	the	the	DET
ajst-2984	49	5	inner	inner	ADJ
ajst-2984	49	6	product	product	NOUN
ajst-2984	49	7	v	v	ADP
ajst-2984	49	8	∙	∙	PROPN
ajst-2984	49	9	is	be	AUX
ajst-2984	49	10	the	the	DET
ajst-2984	49	11	standard	standard	ADJ
ajst-2984	49	12	vector	vector	NOUN
ajst-2984	49	13	dot	dot	NOUN
ajst-2984	49	14	multiplication	multiplication	NOUN
ajst-2984	49	15	,	,	PUNCT
ajst-2984	49	16	that	that	SCONJ
ajst-2984	49	17	is∑	is∑	NOUN
ajst-2984	49	18	,	,	PUNCT
ajst-2984	49	19	|vi|=	|vi|=	PROPN
ajst-2984	49	20	∙	∙	PROPN
ajst-2984	49	21	.	.	PUNCT
ajst-2984	50	1	③the	③the	DET
ajst-2984	50	2	calculated	calculated	ADJ
ajst-2984	50	3	similarity	similarity	NOUN
ajst-2984	50	4	is	be	AUX
ajst-2984	50	5	compared	compare	VERB
ajst-2984	50	6	with	with	ADP
ajst-2984	50	7	the	the	DET
ajst-2984	50	8	filtering	filter	VERB
ajst-2984	50	9	threshold	threshold	NOUN
ajst-2984	50	10	,	,	PUNCT
ajst-2984	50	11	and	and	CCONJ
ajst-2984	50	12	the	the	DET
ajst-2984	50	13	filtering	filter	VERB
ajst-2984	50	14	judgment	judgment	NOUN
ajst-2984	50	15	is	be	AUX
ajst-2984	50	16	made	make	VERB
ajst-2984	50	17	accordingly	accordingly	ADV
ajst-2984	50	18	.	.	PUNCT
ajst-2984	51	1	there	there	PRON
ajst-2984	51	2	are	be	VERB
ajst-2984	51	3	three	three	NUM
ajst-2984	51	4	types	type	NOUN
ajst-2984	51	5	of	of	ADP
ajst-2984	51	6	judgment	judgment	NOUN
ajst-2984	51	7	results	result	NOUN
ajst-2984	51	8	:	:	PUNCT
ajst-2984	51	9	unhealthy	unhealthy	ADJ
ajst-2984	51	10	text	text	NOUN
ajst-2984	51	11	class	class	NOUN
ajst-2984	51	12	,	,	PUNCT
ajst-2984	51	13	which	which	PRON
ajst-2984	51	14	needs	need	VERB
ajst-2984	51	15	to	to	PART
ajst-2984	51	16	be	be	AUX
ajst-2984	51	17	filtered	filter	VERB
ajst-2984	51	18	;	;	PUNCT
ajst-2984	51	19	non	non	ADJ
ajst-2984	51	20	-	-	ADJ
ajst-2984	51	21	unhealthy	unhealthy	ADJ
ajst-2984	51	22	text	text	NOUN
ajst-2984	51	23	class	class	NOUN
ajst-2984	51	24	,	,	PUNCT
ajst-2984	51	25	need	need	VERB
ajst-2984	51	26	to	to	PART
ajst-2984	51	27	pass	pass	VERB
ajst-2984	51	28	;	;	PUNCT
ajst-2984	51	29	suspected	suspect	VERB
ajst-2984	51	30	text	text	NOUN
ajst-2984	51	31	class	class	NOUN
ajst-2984	51	32	,	,	PUNCT
ajst-2984	51	33	need	need	VERB
ajst-2984	51	34	further	further	ADJ
ajst-2984	51	35	judgment	judgment	NOUN
ajst-2984	51	36	.	.	PUNCT
ajst-2984	52	1	the	the	DET
ajst-2984	52	2	algorithm	algorithm	NOUN
ajst-2984	52	3	is	be	AUX
ajst-2984	52	4	described	describe	VERB
ajst-2984	52	5	in	in	ADP
ajst-2984	52	6	detail	detail	NOUN
ajst-2984	52	7	in	in	ADP
ajst-2984	52	8	the	the	DET
ajst-2984	52	9	form	form	NOUN
ajst-2984	52	10	of	of	ADP
ajst-2984	52	11	pseudocode	pseudocode	PROPN
ajst-2984	52	12	below	below	ADV
ajst-2984	52	13	:	:	PUNCT
ajst-2984	52	14	file	file	NOUN
ajst-2984	52	15	name	name	NOUN
ajst-2984	52	16	:	:	PUNCT
ajst-2984	52	17	modeljudge.java	modeljudge.java	PROPN
ajst-2984	52	18	description	description	NOUN
ajst-2984	52	19	:	:	PUNCT
ajst-2984	52	20	“	"	PUNCT
ajst-2984	52	21	unhealthy	unhealthy	ADJ
ajst-2984	52	22	category	category	NOUN
ajst-2984	52	23	pattern	pattern	NOUN
ajst-2984	52	24	filter	filter	NOUN
ajst-2984	52	25	”	"	PUNCT
ajst-2984	52	26	,	,	PUNCT
ajst-2984	52	27	that	that	ADV
ajst-2984	52	28	is	is	ADV
ajst-2984	52	29	,	,	PUNCT
ajst-2984	52	30	unhealthy	unhealthy	ADJ
ajst-2984	52	31	class	class	NOUN
ajst-2984	52	32	prediction	prediction	NOUN
ajst-2984	52	33	model	model	NOUN
ajst-2984	52	34	to	to	PART
ajst-2984	52	35	determine	determine	VERB
ajst-2984	52	36	whether	whether	SCONJ
ajst-2984	52	37	a	a	DET
ajst-2984	52	38	webpage	webpage	NOUN
ajst-2984	52	39	is	be	AUX
ajst-2984	52	40	an	an	DET
ajst-2984	52	41	unhealthy	unhealthy	ADJ
ajst-2984	52	42	webpage	webpage	NOUN
ajst-2984	52	43	input	input	NOUN
ajst-2984	52	44	:	:	PUNCT
ajst-2984	52	45	the	the	DET
ajst-2984	52	46	path	path	NOUN
ajst-2984	52	47	to	to	ADP
ajst-2984	52	48	the	the	DET
ajst-2984	52	49	text	text	NOUN
ajst-2984	52	50	file	file	NOUN
ajst-2984	52	51	or	or	CCONJ
ajst-2984	52	52	web	web	NOUN
ajst-2984	52	53	file	file	NOUN
ajst-2984	52	54	213	213	NUM
ajst-2984	52	55	output	output	NOUN
ajst-2984	52	56	:	:	PUNCT
ajst-2984	52	57	judging	judging	NOUN
ajst-2984	52	58	results	result	NOUN
ajst-2984	52	59	presupposed	presuppose	VERB
ajst-2984	52	60	conditions	condition	NOUN
ajst-2984	52	61	:	:	PUNCT
ajst-2984	52	62	the	the	DET
ajst-2984	52	63	characteristic	characteristic	ADJ
ajst-2984	52	64	vector	vector	NOUN
ajst-2984	52	65	class	class	PROPN
ajst-2984	52	66	st_character=(word	st_character=(word	PROPN
ajst-2984	52	67	,	,	PUNCT
ajst-2984	52	68	f_difference	f_difference	NOUN
ajst-2984	52	69	,	,	PUNCT
ajst-2984	52	70	frequency1	frequency1	PROPN
ajst-2984	52	71	,	,	PUNCT
ajst-2984	52	72	frequency0	frequency0	PROPN
ajst-2984	52	73	)	)	PUNCT
ajst-2984	52	74	,	,	PUNCT
ajst-2984	52	75	where	where	SCONJ
ajst-2984	52	76	word	word	NOUN
ajst-2984	52	77	represents	represent	VERB
ajst-2984	52	78	the	the	DET
ajst-2984	52	79	characteristic	characteristic	ADJ
ajst-2984	52	80	vector	vector	NOUN
ajst-2984	52	81	character	character	NOUN
ajst-2984	52	82	,	,	PUNCT
ajst-2984	52	83	f_difference	f_difference	NOUN
ajst-2984	52	84	represents	represent	VERB
ajst-2984	52	85	the	the	DET
ajst-2984	52	86	word	word	NOUN
ajst-2984	52	87	frequency	frequency	NOUN
ajst-2984	52	88	difference	difference	NOUN
ajst-2984	52	89	,	,	PUNCT
ajst-2984	52	90	frequency1	frequency1	PROPN
ajst-2984	52	91	represents	represent	VERB
ajst-2984	52	92	the	the	DET
ajst-2984	52	93	word	word	NOUN
ajst-2984	52	94	frequency	frequency	NOUN
ajst-2984	52	95	value	value	NOUN
ajst-2984	52	96	in	in	ADP
ajst-2984	52	97	unhealthy	unhealthy	ADJ
ajst-2984	52	98	class	class	NOUN
ajst-2984	52	99	characteristic	characteristic	ADJ
ajst-2984	52	100	vector	vector	NOUN
ajst-2984	52	101	library	library	NOUN
ajst-2984	52	102	,	,	PUNCT
ajst-2984	52	103	and	and	CCONJ
ajst-2984	52	104	frequency0	frequency0	NOUN
ajst-2984	52	105	represents	represent	VERB
ajst-2984	52	106	the	the	DET
ajst-2984	52	107	word	word	NOUN
ajst-2984	52	108	frequency	frequency	NOUN
ajst-2984	52	109	value	value	NOUN
ajst-2984	52	110	in	in	ADP
ajst-2984	52	111	common	common	ADJ
ajst-2984	52	112	class	class	NOUN
ajst-2984	52	113	characteristic	characteristic	ADJ
ajst-2984	52	114	vector	vector	NOUN
ajst-2984	52	115	library	library	NOUN
ajst-2984	52	116	.	.	PUNCT
ajst-2984	53	1	algorithm	algorithm	NOUN
ajst-2984	53	2	steps	step	NOUN
ajst-2984	53	3	:	:	PUNCT
ajst-2984	53	4	step	step	NOUN
ajst-2984	53	5	1	1	NUM
ajst-2984	53	6	:	:	PUNCT
ajst-2984	53	7	initialize	initialize	NOUN
ajst-2984	53	8	:	:	PUNCT
ajst-2984	53	9	step	step	NOUN
ajst-2984	53	10	1.1	1.1	NUM
ajst-2984	53	11	file	file	NOUN
ajst-2984	53	12	type	type	NOUN
ajst-2984	53	13	file	file	NOUN
ajst-2984	53	14	=	=	PRON
ajst-2984	53	15	get	get	VERB
ajst-2984	53	16	the	the	DET
ajst-2984	53	17	test	test	NOUN
ajst-2984	53	18	file	file	NOUN
ajst-2984	53	19	through	through	ADP
ajst-2984	53	20	the	the	DET
ajst-2984	53	21	given	give	VERB
ajst-2984	53	22	path	path	NOUN
ajst-2984	53	23	;	;	PUNCT
ajst-2984	53	24	step	step	VERB
ajst-2984	53	25	1.2	1.2	NUM
ajst-2984	53	26	feature	feature	NOUN
ajst-2984	53	27	class	class	NOUN
ajst-2984	53	28	vlist	vlist	NOUN
ajst-2984	53	29	=	=	PRON
ajst-2984	53	30	get	get	VERB
ajst-2984	53	31	the	the	DET
ajst-2984	53	32	unhealthy	unhealthy	ADJ
ajst-2984	53	33	class	class	NOUN
ajst-2984	53	34	feature	feature	NOUN
ajst-2984	53	35	character	character	NOUN
ajst-2984	53	36	set	set	VERB
ajst-2984	53	37	sorted	sort	VERB
ajst-2984	53	38	by	by	ADP
ajst-2984	53	39	frequency	frequency	NOUN
ajst-2984	53	40	value	value	NOUN
ajst-2984	53	41	from	from	ADP
ajst-2984	53	42	the	the	DET
ajst-2984	53	43	database	database	NOUN
ajst-2984	53	44	;	;	PUNCT
ajst-2984	53	45	step	step	NOUN
ajst-2984	53	46	2	2	NUM
ajst-2984	53	47	:	:	PUNCT
ajst-2984	53	48	perform	perform	VERB
ajst-2984	53	49	unhealthy	unhealthy	ADJ
ajst-2984	53	50	class	class	NOUN
ajst-2984	53	51	feature	feature	NOUN
ajst-2984	53	52	word	word	NOUN
ajst-2984	53	53	frequency	frequency	NOUN
ajst-2984	53	54	statistics	statistic	NOUN
ajst-2984	53	55	on	on	ADP
ajst-2984	53	56	the	the	DET
ajst-2984	53	57	test	test	NOUN
ajst-2984	53	58	file”file	file”file	NOUN
ajst-2984	53	59	”	"	PUNCT
ajst-2984	53	60	,	,	PUNCT
ajst-2984	53	61	and	and	CCONJ
ajst-2984	53	62	put	put	VERB
ajst-2984	53	63	the	the	DET
ajst-2984	53	64	results	result	NOUN
ajst-2984	53	65	into	into	ADP
ajst-2984	53	66	vlist	vlist	NOUN
ajst-2984	53	67	:	:	PUNCT
ajst-2984	53	68	if	if	SCONJ
ajst-2984	53	69	(	(	PUNCT
ajst-2984	53	70	file	file	NOUN
ajst-2984	53	71	is	be	AUX
ajst-2984	53	72	not	not	PART
ajst-2984	53	73	empty	empty	ADJ
ajst-2984	53	74	and	and	CCONJ
ajst-2984	53	75	file	file	NOUN
ajst-2984	53	76	is	be	AUX
ajst-2984	53	77	a	a	DET
ajst-2984	53	78	file	file	NOUN
ajst-2984	53	79	)	)	PUNCT
ajst-2984	53	80	{	{	PUNCT
ajst-2984	53	81	string	string	NOUN
ajst-2984	53	82	type	type	NOUN
ajst-2984	53	83	filetext	filetext	NOUN
ajst-2984	53	84	=	=	NOUN
ajst-2984	53	85	reads	read	NOUN
ajst-2984	53	86	file	file	VERB
ajst-2984	53	87	contents	content	NOUN
ajst-2984	53	88	from	from	ADP
ajst-2984	53	89	file	file	NOUN
ajst-2984	53	90	;	;	PUNCT
ajst-2984	53	91	if	if	SCONJ
ajst-2984	53	92	(	(	PUNCT
ajst-2984	53	93	vlist	vlist	NOUN
ajst-2984	53	94	is	be	AUX
ajst-2984	53	95	not	not	PART
ajst-2984	53	96	empty	empty	ADJ
ajst-2984	53	97	)	)	PUNCT
ajst-2984	53	98	{	{	PUNCT
ajst-2984	53	99	for	for	ADP
ajst-2984	53	100	(	(	PUNCT
ajst-2984	53	101	int	int	NOUN
ajst-2984	53	102	i=0	i=0	PROPN
ajst-2984	53	103	;	;	PUNCT
ajst-2984	53	104	i	i	PRON
ajst-2984	53	105	<	<	X
ajst-2984	53	106	size	size	NOUN
ajst-2984	53	107	of	of	ADP
ajst-2984	53	108	vlist	vlist	NOUN
ajst-2984	53	109	;	;	PUNCT
ajst-2984	53	110	i++	i++	X
ajst-2984	53	111	)	)	PUNCT
ajst-2984	53	112	{	{	PUNCT
ajst-2984	53	113	set	set	VERB
ajst-2984	53	114	the	the	DET
ajst-2984	53	115	frequency0	frequency0	PROPN
ajst-2984	53	116	domain	domain	NOUN
ajst-2984	53	117	of	of	ADP
ajst-2984	53	118	the	the	DET
ajst-2984	53	119	i	i	PROPN
ajst-2984	53	120	-	-	PUNCT
ajst-2984	53	121	th	th	X
ajst-2984	53	122	element	element	NOUN
ajst-2984	53	123	of	of	ADP
ajst-2984	53	124	vlist	vlist	NOUN
ajst-2984	53	125	to	to	ADP
ajst-2984	53	126	0	0	NUM
ajst-2984	53	127	;	;	PUNCT
ajst-2984	53	128	set	set	VERB
ajst-2984	53	129	the	the	DET
ajst-2984	53	130	f_difference1	f_difference1	NUM
ajst-2984	53	131	domain	domain	NOUN
ajst-2984	53	132	of	of	ADP
ajst-2984	53	133	the	the	DET
ajst-2984	53	134	i	i	PROPN
ajst-2984	53	135	-	-	PUNCT
ajst-2984	53	136	th	th	X
ajst-2984	53	137	element	element	NOUN
ajst-2984	53	138	of	of	ADP
ajst-2984	53	139	vlist	vlist	NOUN
ajst-2984	53	140	to	to	ADP
ajst-2984	53	141	0	0	NUM
ajst-2984	53	142	;	;	PUNCT
ajst-2984	53	143	the	the	DET
ajst-2984	53	144	character	character	NOUN
ajst-2984	53	145	corresponding	correspond	VERB
ajst-2984	53	146	to	to	ADP
ajst-2984	53	147	the	the	DET
ajst-2984	53	148	i	i	PROPN
ajst-2984	53	149	-	-	PUNCT
ajst-2984	53	150	th	th	X
ajst-2984	53	151	element	element	NOUN
ajst-2984	53	152	of	of	ADP
ajst-2984	53	153	the	the	DET
ajst-2984	53	154	character	character	NOUN
ajst-2984	53	155	variable	variable	ADJ
ajst-2984	53	156	word	word	NOUN
ajst-2984	53	157	=	=	NOUN
ajst-2984	53	158	vlist	vlist	NOUN
ajst-2984	53	159	;	;	PUNCT
ajst-2984	53	160	count	count	VERB
ajst-2984	53	161	word	word	NOUN
ajst-2984	53	162	frequency	frequency	NOUN
ajst-2984	53	163	in	in	ADP
ajst-2984	53	164	the	the	DET
ajst-2984	53	165	test	test	NOUN
ajst-2984	53	166	document	document	NOUN
ajst-2984	53	167	filetext	filetext	NOUN
ajst-2984	53	168	and	and	CCONJ
ajst-2984	53	169	store	store	VERB
ajst-2984	53	170	it	it	PRON
ajst-2984	53	171	in	in	ADP
ajst-2984	53	172	the	the	DET
ajst-2984	53	173	frequency0	frequency0	PROPN
ajst-2984	53	174	domain	domain	NOUN
ajst-2984	53	175	of	of	ADP
ajst-2984	53	176	the	the	DET
ajst-2984	53	177	i	i	PROPN
ajst-2984	53	178	-	-	PUNCT
ajst-2984	53	179	th	th	X
ajst-2984	53	180	element	element	NOUN
ajst-2984	53	181	of	of	ADP
ajst-2984	53	182	vlist	vlist	NOUN
ajst-2984	53	183	;	;	PUNCT
ajst-2984	53	184	}	}	PUNCT
ajst-2984	53	185	}	}	PUNCT
ajst-2984	53	186	}	}	PUNCT
ajst-2984	53	187	step	step	VERB
ajst-2984	53	188	3	3	NUM
ajst-2984	53	189	:	:	PUNCT
ajst-2984	53	190	using	use	VERB
ajst-2984	53	191	the	the	DET
ajst-2984	53	192	stored	store	VERB
ajst-2984	53	193	values	value	NOUN
ajst-2984	53	194	in	in	ADP
ajst-2984	53	195	the	the	DET
ajst-2984	53	196	feature	feature	NOUN
ajst-2984	53	197	word	word	NOUN
ajst-2984	53	198	class	class	NOUN
ajst-2984	53	199	variable	variable	ADJ
ajst-2984	53	200	vlist	vlist	NOUN
ajst-2984	53	201	,	,	PUNCT
ajst-2984	53	202	a	a	DET
ajst-2984	53	203	prediction	prediction	NOUN
ajst-2984	53	204	algorithm	algorithm	NOUN
ajst-2984	53	205	is	be	AUX
ajst-2984	53	206	used	use	VERB
ajst-2984	53	207	to	to	PART
ajst-2984	53	208	achieve	achieve	VERB
ajst-2984	53	209	classification	classification	NOUN
ajst-2984	53	210	prediction	prediction	NOUN
ajst-2984	53	211	.	.	PUNCT
ajst-2984	54	1	method	method	NOUN
ajst-2984	54	2	1	1	NUM
ajst-2984	54	3	:	:	PUNCT
ajst-2984	54	4	feature	feature	NOUN
ajst-2984	54	5	word	word	NOUN
ajst-2984	54	6	frequency	frequency	NOUN
ajst-2984	54	7	accumulation	accumulation	NOUN
ajst-2984	54	8	,	,	PUNCT
ajst-2984	54	9	the	the	DET
ajst-2984	54	10	algorithm	algorithm	NOUN
ajst-2984	54	11	is	be	AUX
ajst-2984	54	12	:	:	PUNCT
ajst-2984	54	13	floating	float	VERB
ajst-2984	54	14	point	point	NOUN
ajst-2984	54	15	number	number	NOUN
ajst-2984	54	16	type	type	NOUN
ajst-2984	54	17	frqsum=0	frqsum=0	PROPN
ajst-2984	54	18	;	;	PUNCT
ajst-2984	54	19	//cumulative	//cumulative	PUNCT
ajst-2984	54	20	value	value	NOUN
ajst-2984	54	21	of	of	ADP
ajst-2984	54	22	unhealthy	unhealthy	ADJ
ajst-2984	54	23	class	class	NOUN
ajst-2984	54	24	character	character	NOUN
ajst-2984	54	25	frequency	frequency	NOUN
ajst-2984	54	26	in	in	ADP
ajst-2984	54	27	test	test	NOUN
ajst-2984	54	28	sample	sample	NOUN
ajst-2984	54	29	.	.	PUNCT
ajst-2984	55	1	floating	float	VERB
ajst-2984	55	2	point	point	NOUN
ajst-2984	55	3	number	number	NOUN
ajst-2984	55	4	type	type	NOUN
ajst-2984	55	5	frqsum1=0	frqsum1=0	PROPN
ajst-2984	55	6	;	;	PUNCT
ajst-2984	55	7	//cumulative	//cumulative	VERB
ajst-2984	56	1	value	value	NOUN
ajst-2984	56	2	of	of	ADP
ajst-2984	56	3	unhealthy	unhealthy	ADJ
ajst-2984	56	4	class	class	NOUN
ajst-2984	56	5	feature	feature	NOUN
ajst-2984	56	6	word	word	NOUN
ajst-2984	56	7	frequency	frequency	NOUN
ajst-2984	56	8	in	in	ADP
ajst-2984	56	9	unhealthy	unhealthy	ADJ
ajst-2984	56	10	characteristic	characteristic	ADJ
ajst-2984	56	11	vector	vector	NOUN
ajst-2984	56	12	library	library	NOUN
ajst-2984	56	13	.	.	PUNCT
ajst-2984	57	1	for(int	for(int	PROPN
ajst-2984	58	1	i=0	i=0	PROPN
ajst-2984	58	2	;	;	PUNCT
ajst-2984	59	1	i	i	PRON
ajst-2984	59	2	<	<	X
ajst-2984	59	3	size	size	NOUN
ajst-2984	59	4	of	of	ADP
ajst-2984	59	5	vlist	vlist	NOUN
ajst-2984	59	6	;	;	PUNCT
ajst-2984	59	7	i++	i++	X
ajst-2984	59	8	)	)	PUNCT
ajst-2984	59	9	{	{	PUNCT
ajst-2984	59	10	if	if	SCONJ
ajst-2984	59	11	(	(	PUNCT
ajst-2984	59	12	the	the	DET
ajst-2984	59	13	i	i	NOUN
ajst-2984	59	14	-	-	PUNCT
ajst-2984	59	15	th	th	X
ajst-2984	59	16	character	character	NOUN
ajst-2984	59	17	of	of	ADP
ajst-2984	59	18	vlist	vlist	NOUN
ajst-2984	59	19	is	be	AUX
ajst-2984	59	20	chinese	chinese	ADJ
ajst-2984	59	21	)	)	PUNCT
ajst-2984	59	22	{	{	PUNCT
ajst-2984	59	23	frqsum	frqsum	NOUN
ajst-2984	59	24	=	=	SYM
ajst-2984	59	25	frqsum+	frqsum+	ADP
ajst-2984	59	26	the	the	DET
ajst-2984	59	27	domain	domain	NOUN
ajst-2984	59	28	value	value	NOUN
ajst-2984	59	29	of	of	ADP
ajst-2984	59	30	the	the	DET
ajst-2984	59	31	frequency0	frequency0	PROPN
ajst-2984	59	32	domain	domain	NOUN
ajst-2984	59	33	of	of	ADP
ajst-2984	59	34	the	the	DET
ajst-2984	59	35	i	i	PROPN
ajst-2984	59	36	-	-	PUNCT
ajst-2984	59	37	th	th	X
ajst-2984	59	38	element	element	NOUN
ajst-2984	59	39	of	of	ADP
ajst-2984	59	40	vlist	vlist	NOUN
ajst-2984	59	41	;	;	PUNCT
ajst-2984	59	42	frqsum1	frqsum1	PROPN
ajst-2984	59	43	=	=	SYM
ajst-2984	59	44	frqsum1	frqsum1	PROPN
ajst-2984	59	45	+	+	CCONJ
ajst-2984	59	46	the	the	DET
ajst-2984	59	47	domain	domain	NOUN
ajst-2984	59	48	value	value	NOUN
ajst-2984	59	49	of	of	ADP
ajst-2984	59	50	the	the	DET
ajst-2984	59	51	frequency1	frequency1	NOUN
ajst-2984	59	52	domain	domain	NOUN
ajst-2984	59	53	of	of	ADP
ajst-2984	59	54	the	the	DET
ajst-2984	59	55	i	i	PROPN
ajst-2984	59	56	-	-	PUNCT
ajst-2984	59	57	th	th	X
ajst-2984	59	58	element	element	NOUN
ajst-2984	59	59	of	of	ADP
ajst-2984	59	60	vlist	vlist	NOUN
ajst-2984	59	61	;	;	PUNCT
ajst-2984	59	62	}	}	PUNCT
ajst-2984	59	63	}	}	PUNCT
ajst-2984	59	64	if	if	SCONJ
ajst-2984	59	65	(	(	PUNCT
ajst-2984	59	66	|frqsum	|frqsum	NOUN
ajst-2984	59	67	-	-	PUNCT
ajst-2984	59	68	frqsum1|	frqsum1|	NOUN
ajst-2984	59	69	>	>	X
ajst-2984	59	70	changing	change	VERB
ajst-2984	59	71	the	the	DET
ajst-2984	59	72	threshold	threshold	NOUN
ajst-2984	59	73	)	)	PUNCT
ajst-2984	60	1	determine	determine	VERB
ajst-2984	60	2	that	that	SCONJ
ajst-2984	60	3	the	the	DET
ajst-2984	60	4	document	document	NOUN
ajst-2984	60	5	is	be	AUX
ajst-2984	60	6	an	an	DET
ajst-2984	60	7	unhealthy	unhealthy	ADJ
ajst-2984	60	8	class	class	NOUN
ajst-2984	60	9	webpage	webpage	NOUN
ajst-2984	60	10	,	,	PUNCT
ajst-2984	60	11	need	need	VERB
ajst-2984	60	12	to	to	PART
ajst-2984	60	13	filter	filter	VERB
ajst-2984	60	14	;	;	PUNCT
ajst-2984	60	15	else	else	ADV
ajst-2984	60	16	determine	determine	VERB
ajst-2984	60	17	that	that	SCONJ
ajst-2984	60	18	the	the	DET
ajst-2984	60	19	document	document	NOUN
ajst-2984	60	20	is	be	AUX
ajst-2984	60	21	a	a	DET
ajst-2984	60	22	non	non	ADJ
ajst-2984	60	23	-	-	ADJ
ajst-2984	60	24	unhealthy	unhealthy	ADJ
ajst-2984	60	25	webpage	webpage	NOUN
ajst-2984	60	26	,	,	PUNCT
ajst-2984	60	27	passable	passable	ADJ
ajst-2984	60	28	;	;	PUNCT
ajst-2984	60	29	method	method	NOUN
ajst-2984	60	30	2	2	NUM
ajst-2984	60	31	:	:	PUNCT
ajst-2984	60	32	cosine	cosine	NOUN
ajst-2984	60	33	metric	metric	ADJ
ajst-2984	60	34	method	method	NOUN
ajst-2984	60	35	,	,	PUNCT
ajst-2984	60	36	the	the	DET
ajst-2984	60	37	algorithm	algorithm	NOUN
ajst-2984	60	38	is	be	AUX
ajst-2984	60	39	:	:	PUNCT
ajst-2984	60	40	initialize	initialize	VERB
ajst-2984	60	41	floating	float	VERB
ajst-2984	60	42	point	point	NOUN
ajst-2984	60	43	number	number	NOUN
ajst-2984	60	44	type	type	NOUN
ajst-2984	60	45	:	:	PUNCT
ajst-2984	60	46	sim=0	sim=0	PROPN
ajst-2984	60	47	,	,	PUNCT
ajst-2984	60	48	v0v1=0	v0v1=0	ADJ
ajst-2984	60	49	,	,	PUNCT
ajst-2984	60	50	v0v0=0	v0v0=0	NOUN
ajst-2984	60	51	,	,	PUNCT
ajst-2984	60	52	v1v1=0	v1v1=0	ADJ
ajst-2984	60	53	,	,	PUNCT
ajst-2984	60	54	sqrt_v0v0=0	sqrt_v0v0=0	PROPN
ajst-2984	60	55	,	,	PUNCT
ajst-2984	60	56	sqrt_v1v1=0	sqrt_v1v1=0	PROPN
ajst-2984	60	57	;	;	PUNCT
ajst-2984	60	58	for(int	for(int	NOUN
ajst-2984	60	59	i=0	i=0	PROPN
ajst-2984	60	60	;	;	PUNCT
ajst-2984	61	1	i	i	PRON
ajst-2984	61	2	<	<	X
ajst-2984	61	3	size	size	NOUN
ajst-2984	61	4	of	of	ADP
ajst-2984	61	5	vlist	vlist	NOUN
ajst-2984	61	6	;	;	PUNCT
ajst-2984	61	7	i++	i++	NOUN
ajst-2984	61	8	)	)	PUNCT
ajst-2984	61	9	{	{	PUNCT
ajst-2984	61	10	if(the	if(the	PROPN
ajst-2984	61	11	i	i	PROPN
ajst-2984	61	12	-	-	PUNCT
ajst-2984	61	13	th	th	X
ajst-2984	61	14	character	character	NOUN
ajst-2984	61	15	of	of	ADP
ajst-2984	61	16	vlist	vlist	NOUN
ajst-2984	61	17	is	be	AUX
ajst-2984	61	18	chinese	chinese	ADJ
ajst-2984	61	19	)	)	PUNCT
ajst-2984	61	20	{	{	PUNCT
ajst-2984	61	21	v0v1+=the	v0v1+=the	DET
ajst-2984	61	22	domain	domain	NOUN
ajst-2984	61	23	value	value	NOUN
ajst-2984	61	24	of	of	ADP
ajst-2984	61	25	the	the	DET
ajst-2984	61	26	frequency0	frequency0	PROPN
ajst-2984	61	27	domain	domain	NOUN
ajst-2984	61	28	of	of	ADP
ajst-2984	61	29	the	the	DET
ajst-2984	61	30	i	i	PROPN
ajst-2984	61	31	-	-	PUNCT
ajst-2984	61	32	th	th	X
ajst-2984	61	33	element	element	NOUN
ajst-2984	61	34	of	of	ADP
ajst-2984	61	35	vlist	vlist	NOUN
ajst-2984	61	36	*	*	PUNCT
ajst-2984	61	37	the	the	DET
ajst-2984	61	38	domain	domain	NOUN
ajst-2984	61	39	value	value	NOUN
ajst-2984	61	40	of	of	ADP
ajst-2984	61	41	the	the	DET
ajst-2984	61	42	frequency1	frequency1	NOUN
ajst-2984	61	43	domain	domain	NOUN
ajst-2984	61	44	of	of	ADP
ajst-2984	61	45	the	the	DET
ajst-2984	61	46	i	i	PROPN
ajst-2984	61	47	-	-	PUNCT
ajst-2984	61	48	th	th	X
ajst-2984	61	49	element	element	NOUN
ajst-2984	61	50	of	of	ADP
ajst-2984	61	51	vlist	vlist	NOUN
ajst-2984	61	52	;	;	PUNCT
ajst-2984	61	53	v0v0+=the	v0v0+=the	DET
ajst-2984	61	54	domain	domain	NOUN
ajst-2984	61	55	value	value	NOUN
ajst-2984	61	56	of	of	ADP
ajst-2984	61	57	the	the	DET
ajst-2984	61	58	frequency0	frequency0	PROPN
ajst-2984	61	59	domain	domain	NOUN
ajst-2984	61	60	of	of	ADP
ajst-2984	61	61	the	the	DET
ajst-2984	61	62	i	i	PROPN
ajst-2984	61	63	-	-	PUNCT
ajst-2984	61	64	th	th	X
ajst-2984	61	65	element	element	NOUN
ajst-2984	61	66	of	of	ADP
ajst-2984	61	67	vlist	vlist	NOUN
ajst-2984	61	68	*	*	PUNCT
ajst-2984	61	69	the	the	DET
ajst-2984	61	70	domain	domain	NOUN
ajst-2984	61	71	value	value	NOUN
ajst-2984	61	72	of	of	ADP
ajst-2984	61	73	the	the	DET
ajst-2984	61	74	frequency0	frequency0	PROPN
ajst-2984	61	75	domain	domain	NOUN
ajst-2984	61	76	of	of	ADP
ajst-2984	61	77	the	the	DET
ajst-2984	61	78	i	i	PROPN
ajst-2984	61	79	-	-	PUNCT
ajst-2984	61	80	th	th	X
ajst-2984	61	81	element	element	NOUN
ajst-2984	61	82	of	of	ADP
ajst-2984	61	83	vlist	vlist	NOUN
ajst-2984	61	84	;	;	PUNCT
ajst-2984	61	85	v1v1+=the	v1v1+=the	DET
ajst-2984	61	86	domain	domain	NOUN
ajst-2984	61	87	value	value	NOUN
ajst-2984	61	88	of	of	ADP
ajst-2984	61	89	the	the	DET
ajst-2984	61	90	frequency1	frequency1	NOUN
ajst-2984	61	91	domain	domain	NOUN
ajst-2984	61	92	of	of	ADP
ajst-2984	61	93	the	the	DET
ajst-2984	61	94	i	i	PROPN
ajst-2984	61	95	-	-	PUNCT
ajst-2984	61	96	th	th	X
ajst-2984	61	97	element	element	NOUN
ajst-2984	61	98	of	of	ADP
ajst-2984	61	99	vlist	vlist	NOUN
ajst-2984	61	100	*	*	PUNCT
ajst-2984	61	101	the	the	DET
ajst-2984	61	102	domain	domain	NOUN
ajst-2984	61	103	value	value	NOUN
ajst-2984	61	104	of	of	ADP
ajst-2984	61	105	the	the	DET
ajst-2984	61	106	frequency1	frequency1	NOUN
ajst-2984	61	107	domain	domain	NOUN
ajst-2984	61	108	of	of	ADP
ajst-2984	61	109	the	the	DET
ajst-2984	61	110	i	i	PROPN
ajst-2984	61	111	-	-	PUNCT
ajst-2984	61	112	th	th	X
ajst-2984	61	113	element	element	NOUN
ajst-2984	61	114	of	of	ADP
ajst-2984	61	115	vlist	vlist	NOUN
ajst-2984	61	116	;	;	PUNCT
ajst-2984	61	117	}	}	PUNCT
ajst-2984	61	118	}	}	PUNCT
ajst-2984	61	119	sqrt_v0v0	sqrt_v0v0	NOUN
ajst-2984	61	120	=	=	SYM
ajst-2984	61	121	square(v0v0	square(v0v0	NOUN
ajst-2984	61	122	)	)	PUNCT
ajst-2984	61	123	;	;	PUNCT
ajst-2984	61	124	sqrt_v1v1	sqrt_v1v1	NOUN
ajst-2984	61	125	=	=	PROPN
ajst-2984	61	126	square(v1v1	square(v1v1	NOUN
ajst-2984	61	127	)	)	PUNCT
ajst-2984	61	128	;	;	PUNCT
ajst-2984	61	129	sim	sim	NOUN
ajst-2984	61	130	=	=	SYM
ajst-2984	61	131	v0v1/(sqrt_v0v0*sqrt_v1v1	v0v1/(sqrt_v0v0*sqrt_v1v1	ADJ
ajst-2984	61	132	)	)	PUNCT
ajst-2984	61	133	;	;	PUNCT
ajst-2984	61	134	if(sim	if(sim	PROPN
ajst-2984	61	135	>	>	X
ajst-2984	61	136	changing	change	VERB
ajst-2984	61	137	the	the	DET
ajst-2984	61	138	threshold	threshold	NOUN
ajst-2984	61	139	)	)	PUNCT
ajst-2984	61	140	determine	determine	VERB
ajst-2984	61	141	that	that	SCONJ
ajst-2984	61	142	the	the	DET
ajst-2984	61	143	document	document	NOUN
ajst-2984	61	144	is	be	AUX
ajst-2984	61	145	an	an	DET
ajst-2984	61	146	unhealthy	unhealthy	ADJ
ajst-2984	61	147	class	class	NOUN
ajst-2984	61	148	webpage	webpage	NOUN
ajst-2984	61	149	,	,	PUNCT
ajst-2984	61	150	need	need	VERB
ajst-2984	61	151	to	to	PART
ajst-2984	61	152	filter	filter	VERB
ajst-2984	61	153	;	;	PUNCT
ajst-2984	61	154	else	else	ADV
ajst-2984	61	155	determine	determine	VERB
ajst-2984	61	156	that	that	SCONJ
ajst-2984	61	157	the	the	DET
ajst-2984	61	158	document	document	NOUN
ajst-2984	61	159	is	be	AUX
ajst-2984	61	160	a	a	DET
ajst-2984	61	161	nonunhealthy	nonunhealthy	ADJ
ajst-2984	61	162	webpage	webpage	NOUN
ajst-2984	61	163	,	,	PUNCT
ajst-2984	61	164	passable	passable	ADJ
ajst-2984	61	165	;	;	PUNCT
ajst-2984	61	166	7	7	X
ajst-2984	61	167	.	.	X
ajst-2984	61	168	experimental	experimental	ADJ
ajst-2984	61	169	results	result	NOUN
ajst-2984	61	170	and	and	CCONJ
ajst-2984	61	171	analysis	analysis	NOUN
ajst-2984	61	172	this	this	DET
ajst-2984	61	173	paper	paper	NOUN
ajst-2984	61	174	selects	select	VERB
ajst-2984	61	175	100	100	NUM
ajst-2984	61	176	documents	document	NOUN
ajst-2984	61	177	as	as	ADP
ajst-2984	61	178	test	test	NOUN
ajst-2984	61	179	documents	document	NOUN
ajst-2984	61	180	,	,	PUNCT
ajst-2984	61	181	including	include	VERB
ajst-2984	61	182	15	15	NUM
ajst-2984	61	183	unhealthy	unhealthy	ADJ
ajst-2984	61	184	documents	document	NOUN
ajst-2984	61	185	,	,	PUNCT
ajst-2984	61	186	70	70	NUM
ajst-2984	61	187	common	common	ADJ
ajst-2984	61	188	documents	document	NOUN
ajst-2984	61	189	,	,	PUNCT
ajst-2984	61	190	10	10	NUM
ajst-2984	61	191	sexual	sexual	ADJ
ajst-2984	61	192	medicine	medicine	NOUN
ajst-2984	61	193	documents	document	NOUN
ajst-2984	61	194	and	and	CCONJ
ajst-2984	61	195	5	5	NUM
ajst-2984	61	196	sexual	sexual	ADJ
ajst-2984	61	197	literature	literature	NOUN
ajst-2984	61	198	documents	document	NOUN
ajst-2984	61	199	.	.	PUNCT
ajst-2984	62	1	the	the	DET
ajst-2984	62	2	experimental	experimental	ADJ
ajst-2984	62	3	results	result	NOUN
ajst-2984	62	4	are	be	AUX
ajst-2984	62	5	shown	show	VERB
ajst-2984	62	6	in	in	ADP
ajst-2984	62	7	table	table	NOUN
ajst-2984	62	8	1	1	NUM
ajst-2984	62	9	:	:	PUNCT
ajst-2984	62	10	it	it	PRON
ajst-2984	62	11	is	be	AUX
ajst-2984	62	12	concluded	conclude	VERB
ajst-2984	62	13	that	that	SCONJ
ajst-2984	62	14	word	word	NOUN
ajst-2984	62	15	frequency	frequency	NOUN
ajst-2984	62	16	accumulation	accumulation	NOUN
ajst-2984	62	17	and	and	CCONJ
ajst-2984	62	18	cosine	cosine	NOUN
ajst-2984	62	19	measure	measure	NOUN
ajst-2984	62	20	algorithm	algorithm	NOUN
ajst-2984	62	21	can	can	AUX
ajst-2984	62	22	filter	filter	VERB
ajst-2984	62	23	unhealthy	unhealthy	ADJ
ajst-2984	62	24	webpages	webpage	NOUN
ajst-2984	62	25	with	with	ADP
ajst-2984	62	26	very	very	ADV
ajst-2984	62	27	high	high	ADJ
ajst-2984	62	28	accuracy	accuracy	NOUN
ajst-2984	62	29	from	from	ADP
ajst-2984	62	30	table	table	NOUN
ajst-2984	62	31	1	1	NUM
ajst-2984	62	32	;	;	PUNCT
ajst-2984	62	33	although	although	SCONJ
ajst-2984	62	34	the	the	DET
ajst-2984	62	35	feature	feature	NOUN
ajst-2984	62	36	word	word	NOUN
ajst-2984	62	37	frequency	frequency	NOUN
ajst-2984	62	38	accumulation	accumulation	NOUN
ajst-2984	62	39	method	method	NOUN
ajst-2984	62	40	has	have	VERB
ajst-2984	62	41	higher	high	ADJ
ajst-2984	62	42	accuracy	accuracy	NOUN
ajst-2984	62	43	in	in	ADP
ajst-2984	62	44	filtering	filter	VERB
ajst-2984	62	45	unhealthy	unhealthy	ADJ
ajst-2984	62	46	webpages	webpage	NOUN
ajst-2984	62	47	,	,	PUNCT
ajst-2984	62	48	it	it	PRON
ajst-2984	62	49	is	be	AUX
ajst-2984	62	50	worse	bad	ADJ
ajst-2984	62	51	than	than	ADP
ajst-2984	62	52	cosine	cosine	NOUN
ajst-2984	62	53	measure	measure	NOUN
ajst-2984	62	54	method	method	NOUN
ajst-2984	62	55	in	in	ADP
ajst-2984	62	56	identifying	identify	VERB
ajst-2984	62	57	sexual	sexual	ADJ
ajst-2984	62	58	medical	medical	ADJ
ajst-2984	62	59	webpages	webpage	NOUN
ajst-2984	62	60	.	.	PUNCT
ajst-2984	63	1	table	table	NOUN
ajst-2984	63	2	1	1	NUM
ajst-2984	63	3	.	.	PUNCT
ajst-2984	64	1	experimental	experimental	ADJ
ajst-2984	64	2	results	result	NOUN
ajst-2984	64	3	default	default	NOUN
ajst-2984	64	4	threshold	threshold	NOUN
ajst-2984	64	5	statistics	statistic	NOUN
ajst-2984	64	6	of	of	ADP
ajst-2984	64	7	the	the	DET
ajst-2984	64	8	number	number	NOUN
ajst-2984	64	9	of	of	ADP
ajst-2984	64	10	unhealthy	unhealthy	ADJ
ajst-2984	64	11	class	class	NOUN
ajst-2984	64	12	documents	document	NOUN
ajst-2984	64	13	statistics	statistic	NOUN
ajst-2984	64	14	of	of	ADP
ajst-2984	64	15	the	the	DET
ajst-2984	64	16	number	number	NOUN
ajst-2984	64	17	of	of	ADP
ajst-2984	64	18	nonunhealthy	nonunhealthy	ADJ
ajst-2984	64	19	class	class	NOUN
ajst-2984	64	20	documents	document	NOUN
ajst-2984	64	21	misjudgments	misjudgment	NOUN
ajst-2984	64	22	(	(	PUNCT
ajst-2984	64	23	upper	upper	ADJ
ajst-2984	64	24	limit	limit	NOUN
ajst-2984	64	25	of	of	ADP
ajst-2984	64	26	misjudged	misjudge	VERB
ajst-2984	64	27	documents	document	NOUN
ajst-2984	64	28	)	)	PUNCT
ajst-2984	64	29	accuracy	accuracy	NOUN
ajst-2984	64	30	total	total	ADJ
ajst-2984	64	31	number	number	NOUN
ajst-2984	64	32	of	of	ADP
ajst-2984	64	33	misjudged	misjudge	VERB
ajst-2984	64	34	documents(100	documents(100	NOUN
ajst-2984	64	35	)	)	PUNCT
ajst-2984	64	36	number	number	NOUN
ajst-2984	64	37	of	of	ADP
ajst-2984	64	38	misjudged	misjudge	VERB
ajst-2984	64	39	common	common	ADJ
ajst-2984	64	40	class	class	NOUN
ajst-2984	64	41	documents(70	documents(70	ADJ
ajst-2984	64	42	)	)	PUNCT
ajst-2984	64	43	number	number	NOUN
ajst-2984	64	44	of	of	ADP
ajst-2984	64	45	misjudged	misjudge	VERB
ajst-2984	64	46	sex	sex	NOUN
ajst-2984	64	47	medical	medical	ADJ
ajst-2984	64	48	documents(10	documents(10	NOUN
ajst-2984	64	49	)	)	PUNCT
ajst-2984	64	50	number	number	NOUN
ajst-2984	64	51	of	of	ADP
ajst-2984	64	52	misjudged	misjudge	VERB
ajst-2984	64	53	sex	sex	NOUN
ajst-2984	64	54	literature	literature	NOUN
ajst-2984	64	55	documents(5	documents(5	PROPN
ajst-2984	64	56	)	)	PUNCT
ajst-2984	64	57	number	number	NOUN
ajst-2984	64	58	of	of	ADP
ajst-2984	64	59	unhealthy	unhealthy	ADJ
ajst-2984	64	60	class	class	NOUN
ajst-2984	64	61	documents(15	documents(15	NOUN
ajst-2984	64	62	)	)	PUNCT
ajst-2984	64	63	the	the	DET
ajst-2984	64	64	real	real	ADJ
ajst-2984	64	65	situation	situation	NOUN
ajst-2984	64	66	15	15	NUM
ajst-2984	64	67	85	85	NUM
ajst-2984	64	68	0	0	NUM
ajst-2984	64	69	0	0	NUM
ajst-2984	64	70	0	0	NUM
ajst-2984	64	71	0	0	NUM
ajst-2984	64	72	0	0	NUM
ajst-2984	64	73	characteristic	characteristic	ADJ
ajst-2984	64	74	vector	vector	NOUN
ajst-2984	64	75	word	word	NOUN
ajst-2984	64	76	frequency	frequency	NOUN
ajst-2984	64	77	accumulation	accumulation	NOUN
ajst-2984	64	78	method	method	NOUN
ajst-2984	64	79	12	12	NUM
ajst-2984	64	80	18	18	NUM
ajst-2984	64	81	82	82	NUM
ajst-2984	64	82	12	12	NUM
ajst-2984	64	83	2	2	NUM
ajst-2984	64	84	5	5	NUM
ajst-2984	64	85	4	4	NUM
ajst-2984	64	86	1	1	NUM
ajst-2984	64	87	88	88	NUM
ajst-2984	64	88	%	%	NOUN
ajst-2984	64	89	cosine	cosine	NOUN
ajst-2984	64	90	metric	metric	ADJ
ajst-2984	64	91	method	method	NOUN
ajst-2984	64	92	0.6	0.6	NUM
ajst-2984	64	93	13	13	NUM
ajst-2984	64	94	87	87	NUM
ajst-2984	64	95	14	14	NUM
ajst-2984	64	96	4	4	NUM
ajst-2984	64	97	3	3	NUM
ajst-2984	64	98	4	4	NUM
ajst-2984	64	99	3	3	NUM
ajst-2984	64	100	86	86	NUM
ajst-2984	64	101	%	%	NOUN
ajst-2984	64	102	214	214	NUM
ajst-2984	64	103	acknowledgment	acknowledgment	NOUN
ajst-2984	64	104	this	this	DET
ajst-2984	64	105	work	work	NOUN
ajst-2984	64	106	was	be	AUX
ajst-2984	64	107	supported	support	VERB
ajst-2984	64	108	by	by	ADP
ajst-2984	64	109	the	the	DET
ajst-2984	64	110	science	science	NOUN
ajst-2984	64	111	and	and	CCONJ
ajst-2984	64	112	technology	technology	NOUN
ajst-2984	64	113	project	project	NOUN
ajst-2984	64	114	of	of	ADP
ajst-2984	64	115	jiangxi	jiangxi	PROPN
ajst-2984	64	116	provincial	provincial	PROPN
ajst-2984	64	117	department	department	PROPN
ajst-2984	64	118	of	of	ADP
ajst-2984	64	119	education	education	NOUN
ajst-2984	64	120	,	,	PUNCT
ajst-2984	64	121	and	and	CCONJ
ajst-2984	64	122	the	the	DET
ajst-2984	64	123	project	project	NOUN
ajst-2984	64	124	number	number	NOUN
ajst-2984	64	125	is	be	AUX
ajst-2984	64	126	gjj170797	gjj170797	NOUN
ajst-2984	64	127	.	.	PUNCT
ajst-2984	65	1	references	reference	NOUN
ajst-2984	65	2	[	[	X
ajst-2984	66	1	1	1	NUM
ajst-2984	66	2	]	]	PUNCT
ajst-2984	66	3	zhu	zhu	PROPN
ajst-2984	66	4	guojie.research	guojie.research	NOUN
ajst-2984	66	5	and	and	CCONJ
ajst-2984	66	6	implementation	implementation	NOUN
ajst-2984	66	7	of	of	ADP
ajst-2984	66	8	bad	bad	ADJ
ajst-2984	66	9	webpage	webpage	NOUN
ajst-2984	66	10	detection	detection	NOUN
ajst-2984	66	11	system	system	NOUN
ajst-2984	66	12	based	base	VERB
ajst-2984	66	13	on	on	ADP
ajst-2984	66	14	text	text	NOUN
ajst-2984	66	15	features	feature	NOUN
ajst-2984	66	16	[	[	X
ajst-2984	66	17	d].zhejiang	d].zhejiang	NOUN
ajst-2984	66	18	university	university	NOUN
ajst-2984	66	19	.	.	PUNCT
ajst-2984	67	1	2020	2020	NUM
ajst-2984	67	2	.	.	PUNCT
ajst-2984	68	1	[	[	X
ajst-2984	68	2	2	2	X
ajst-2984	68	3	]	]	PUNCT
ajst-2984	68	4	wang	wang	PROPN
ajst-2984	68	5	lei.research	lei.research	PROPN
ajst-2984	68	6	on	on	ADP
ajst-2984	68	7	double	double	ADJ
ajst-2984	68	8	filtering	filtering	NOUN
ajst-2984	68	9	method	method	NOUN
ajst-2984	68	10	of	of	ADP
ajst-2984	68	11	bad	bad	ADJ
ajst-2984	68	12	web	web	NOUN
ajst-2984	68	13	pages	page	NOUN
ajst-2984	68	14	based	base	VERB
ajst-2984	68	15	on	on	ADP
ajst-2984	68	16	content	content	NOUN
ajst-2984	68	17	recognition	recognition	NOUN
ajst-2984	69	1	[	[	X
ajst-2984	69	2	d	d	X
ajst-2984	69	3	]	]	X
ajst-2984	69	4	.	.	PUNCT
ajst-2984	70	1	jilin	jilin	PROPN
ajst-2984	70	2	university	university	PROPN
ajst-2984	70	3	.	.	PUNCT
ajst-2984	70	4	2012	2012	NUM
ajst-2984	70	5	.	.	PUNCT
ajst-2984	71	1	[	[	X
ajst-2984	71	2	3	3	X
ajst-2984	71	3	]	]	X
ajst-2984	71	4	si	si	PROPN
ajst-2984	71	5	derui	derui	PROPN
ajst-2984	71	6	.	.	PUNCT
ajst-2984	72	1	research	research	NOUN
ajst-2984	72	2	on	on	ADP
ajst-2984	72	3	web	web	NOUN
ajst-2984	72	4	filtering	filtering	NOUN
ajst-2984	72	5	technology	technology	NOUN
ajst-2984	72	6	based	base	VERB
ajst-2984	72	7	on	on	ADP
ajst-2984	72	8	text	text	NOUN
ajst-2984	72	9	content	content	NOUN
ajst-2984	73	1	[	[	X
ajst-2984	73	2	d	d	X
ajst-2984	73	3	]	]	X
ajst-2984	73	4	.	.	PUNCT
ajst-2984	74	1	lanzhou	lanzhou	PROPN
ajst-2984	74	2	university	university	PROPN
ajst-2984	74	3	.	.	PUNCT
ajst-2984	75	1	2008	2008	NUM
ajst-2984	75	2	.	.	PUNCT
ajst-2984	76	1	[	[	X
ajst-2984	76	2	4	4	X
ajst-2984	76	3	]	]	PUNCT
ajst-2984	76	4	jiawei	jiawei	PROPN
ajst-2984	76	5	han	han	PROPN
ajst-2984	76	6	,	,	PUNCT
ajst-2984	76	7	fan	fan	PROPN
ajst-2984	76	8	ming&meng	ming&meng	PROPN
ajst-2984	76	9	xiaofeng	xiaofeng	PROPN
ajst-2984	76	10	.	.	PUNCT
ajst-2984	77	1	data	data	PROPN
ajst-2984	77	2	mining	mining	NOUN
ajst-2984	77	3	concept	concept	NOUN
ajst-2984	77	4	and	and	CCONJ
ajst-2984	77	5	technology	technology	NOUN
ajst-2984	77	6	(	(	PUNCT
ajst-2984	77	7	3rd	3rd	NOUN
ajst-2984	77	8	edition	edition	NOUN
ajst-2984	77	9	)	)	PUNCT
ajst-2984	77	10	.	.	PUNCT
ajst-2984	78	1	machinery	machinery	NOUN
ajst-2984	78	2	industry	industry	NOUN
ajst-2984	78	3	press	press	NOUN
ajst-2984	78	4	.	.	PUNCT
ajst-2984	79	1	2012	2012	NUM
ajst-2984	79	2	.	.	PUNCT
ajst-2984	80	1	[	[	X
ajst-2984	80	2	5	5	NUM
ajst-2984	80	3	]	]	X
ajst-2984	80	4	tang	tang	PROPN
ajst-2984	80	5	jiangang	jiangang	PROPN
ajst-2984	80	6	,	,	PUNCT
ajst-2984	80	7	xiong	xiong	PROPN
ajst-2984	80	8	guoping	guoping	PROPN
ajst-2984	80	9	.	.	PUNCT
ajst-2984	81	1	research	research	NOUN
ajst-2984	81	2	and	and	CCONJ
ajst-2984	81	3	application	application	NOUN
ajst-2984	81	4	about	about	ADP
ajst-2984	81	5	unhealthy	unhealthy	ADJ
ajst-2984	81	6	webpage	webpage	NOUN
ajst-2984	81	7	filter	filter	NOUN
ajst-2984	81	8	model	model	NOUN
ajst-2984	81	9	based	base	VERB
ajst-2984	81	10	on	on	ADP
ajst-2984	81	11	words	word	NOUN
ajst-2984	81	12	’	'	PUNCT
ajst-2984	81	13	frequency	frequency	NOUN
ajst-2984	81	14	and	and	CCONJ
ajst-2984	81	15	datamining	datamine	VERB
ajst-2984	81	16	technology[j	technology[j	PROPN
ajst-2984	81	17	]	]	PUNCT
ajst-2984	81	18	.	.	PUNCT
ajst-2984	82	1	journal	journal	PROPN
ajst-2984	82	2	of	of	ADP
ajst-2984	82	3	xiamen	xiamen	PROPN
ajst-2984	82	4	university	university	PROPN
ajst-2984	82	5	(	(	PUNCT
ajst-2984	82	6	natural	natural	ADJ
ajst-2984	82	7	science	science	NOUN
ajst-2984	82	8	)	)	PUNCT
ajst-2984	82	9	,	,	PUNCT
ajst-2984	82	10	2007(11	2007(11	NUM
ajst-2984	82	11	)	)	PUNCT
ajst-2984	82	12	.	.	PUNCT
ajst-2984	83	1	[	[	X
ajst-2984	83	2	6	6	NUM
ajst-2984	83	3	]	]	PUNCT
ajst-2984	83	4	ronghua	ronghua	PROPN
ajst-2984	83	5	lu	lu	PROPN
ajst-2984	83	6	.	.	PUNCT
ajst-2984	84	1	design	design	NOUN
ajst-2984	84	2	of	of	ADP
ajst-2984	84	3	bad	bad	ADJ
ajst-2984	84	4	information	information	NOUN
ajst-2984	84	5	filtering	filter	VERB
ajst-2984	84	6	system	system	NOUN
ajst-2984	84	7	for	for	ADP
ajst-2984	84	8	web	web	NOUN
ajst-2984	84	9	pages[j	pages[j	PROPN
ajst-2984	84	10	]	]	PUNCT
ajst-2984	84	11	.	.	PUNCT
ajst-2984	85	1	frontiers	frontier	NOUN
ajst-2984	85	2	in	in	ADP
ajst-2984	85	3	computing	computing	NOUN
ajst-2984	85	4	and	and	CCONJ
ajst-2984	85	5	intelligent	intelligent	ADJ
ajst-2984	85	6	systems	system	NOUN
ajst-2984	85	7	,	,	PUNCT
ajst-2984	85	8	2022(3	2022(3	NUM
ajst-2984	85	9	)	)	PUNCT
ajst-2984	85	10	.	.	PUNCT
ajst-2984	86	1	[	[	X
ajst-2984	86	2	7	7	X
ajst-2984	86	3	]	]	X
ajst-2984	86	4	yao	yao	PROPN
ajst-2984	86	5	mei	mei	PROPN
ajst-2984	86	6	.	.	PUNCT
ajst-2984	87	1	research	research	NOUN
ajst-2984	87	2	on	on	ADP
ajst-2984	87	3	key	key	ADJ
ajst-2984	87	4	technologies	technology	NOUN
ajst-2984	87	5	based	base	VERB
ajst-2984	87	6	on	on	ADP
ajst-2984	87	7	web	web	NOUN
ajst-2984	87	8	content	content	NOUN
ajst-2984	87	9	filtering	filter	VERB
ajst-2984	88	1	[	[	X
ajst-2984	88	2	j	j	X
ajst-2984	88	3	]	]	X
ajst-2984	88	4	.	.	PUNCT
ajst-2984	89	1	information	information	NOUN
ajst-2984	89	2	and	and	CCONJ
ajst-2984	89	3	computer	computer	NOUN
ajst-2984	89	4	(	(	PUNCT
ajst-2984	89	5	theoretical	theoretical	ADJ
ajst-2984	89	6	edition	edition	NOUN
ajst-2984	89	7	.	.	PUNCT
ajst-2984	90	1	2022	2022	NUM
ajst-2984	90	2	(	(	PUNCT
ajst-2984	90	3	14	14	NUM
ajst-2984	90	4	)	)	PUNCT
ajst-2984	90	5	.	.	PUNCT