{"id":"https://openalex.org/W1503141391","doi":"https://doi.org/10.1109/wi.2003.1241198","title":"Two-phase Web site classification based on hidden Markov tree models","display_name":"Two-phase Web site classification based on hidden Markov tree models","publication_year":2003,"publication_date":"2003-01-01","ids":{"openalex":"https://openalex.org/W1503141391","doi":"https://doi.org/10.1109/wi.2003.1241198","mag":"1503141391"},"language":"en","primary_location":{"id":"doi:10.1109/wi.2003.1241198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wi.2003.1241198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings IEEE/WIC International Conference on Web Intelligence (WI 2003)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023918894","display_name":"Yonghong Tian","orcid":"https://orcid.org/0000-0002-2978-5935"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"YongHong Tian","raw_affiliation_strings":["Digital Media Lab, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","Graduate School of Chinese Academy of Sciences, Research Center for Digital Media, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Media Lab, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Graduate School of Chinese Academy of Sciences, Research Center for Digital Media, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028898556","display_name":"Tiejun Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"TieJun Huang","raw_affiliation_strings":["Digital Media Lab, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","Graduate School of Chinese Academy of Sciences, Research Center for Digital Media, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Digital Media Lab, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Graduate School of Chinese Academy of Sciences, Research Center for Digital Media, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100865935","display_name":"Wen Gao","orcid":"https://orcid.org/0009-0002-0139-2627"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen Gao","raw_affiliation_strings":["Department of Computer Science, Harbin Institute of Technology, Harbin, China","Digital Media Lab, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","Graduate School of Chinese Academy of Sciences, Research Center for Digital Media, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Digital Media Lab, Institute of Computing Technology, Chinese Academy and Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Graduate School of Chinese Academy of Sciences, Research Center for Digital Media, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101705358","display_name":"Jun Cheng","orcid":"https://orcid.org/0000-0002-3131-3275"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Cheng","raw_affiliation_strings":["Graduate School of Chinese Academy of Sciences, Research Center for Digital Media, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Chinese Academy of Sciences, Research Center for Digital Media, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109851009","display_name":"PingBo Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"PingBo Kang","raw_affiliation_strings":["Graduate School of Chinese Academy of Sciences, Research Center for Digital Media, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Chinese Academy of Sciences, Research Center for Digital Media, Beijing, China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2769,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.78781711,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"6","issue":null,"first_page":"227","last_page":"234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8109866976737976},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.5398281216621399},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5383942723274231},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5052328705787659},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4719114899635315},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4656928777694702},{"id":"https://openalex.org/keywords/web-site","display_name":"Web site","score":0.4475199580192566},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4395422637462616},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.42879554629325867},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37738046050071716},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.2531203627586365},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.2151651680469513},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18432405591011047},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09598201513290405},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.08729934692382812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8109866976737976},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.5398281216621399},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5383942723274231},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5052328705787659},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4719114899635315},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4656928777694702},{"id":"https://openalex.org/C2984519610","wikidata":"https://www.wikidata.org/wiki/Q35127","display_name":"Web site","level":3,"score":0.4475199580192566},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4395422637462616},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.42879554629325867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37738046050071716},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.2531203627586365},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.2151651680469513},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18432405591011047},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09598201513290405},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.08729934692382812},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wi.2003.1241198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wi.2003.1241198","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings IEEE/WIC International Conference on Web Intelligence (WI 2003)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1482260847","https://openalex.org/W1568850833","https://openalex.org/W2005124845","https://openalex.org/W2063862666","https://openalex.org/W2065168033","https://openalex.org/W2067223933","https://openalex.org/W2068863058","https://openalex.org/W2076008912","https://openalex.org/W2097614116","https://openalex.org/W2112335400","https://openalex.org/W2113475061","https://openalex.org/W2134929491","https://openalex.org/W2149136862","https://openalex.org/W2152321560","https://openalex.org/W2153662613","https://openalex.org/W2159492648","https://openalex.org/W2168796889","https://openalex.org/W6676918204"],"related_works":["https://openalex.org/W2613891979","https://openalex.org/W1857685597","https://openalex.org/W87158434","https://openalex.org/W2359999795","https://openalex.org/W2503502284","https://openalex.org/W2064945795","https://openalex.org/W3002947890","https://openalex.org/W2156420263","https://openalex.org/W2479660196","https://openalex.org/W11343035"],"abstract_inverted_index":{"With":[0],"the":[1,6,11,14,37,49,83,92,96,99,108,112,116,131,151,159],"exponential":[2],"growth":[3],"of":[4,10,19,43,111,134],"both":[5],"amount":[7],"and":[8,40,71,115,119,182],"diversity":[9],"information":[12,42],"that":[13],"Web":[15,21,32,44,135,165],"encompasses,":[16],"automatic":[17],"classification":[18,34,141,161],"topic-specific":[20],"sites":[22,136,166],"is":[23,52,62,75,105,123,146,176],"highly":[24],"desirable.":[25],"We":[26],"propose":[27],"a":[28,55,65,72,168],"novel":[29],"approach":[30,145,175],"for":[31,125,129,163],"site":[33,50,73,113,152],"based":[35],"on":[36],"content,":[38],"structure":[39,51],"context":[41,86],"sites.":[45],"In":[46],"our":[47,174],"approach,":[48],"represented":[53],"as":[54,64,107],"two-layered":[56],"tree":[57,70,74,102,114],"in":[58,95],"which":[59],"each":[60],"page":[61],"modeled":[63],"DOM":[66,117],"(document":[67],"object":[68],"model)":[69],"used":[76],"to":[77,90,148,178],"hierarchically":[78],"link":[79],"all":[80],"pages":[81],"within":[82],"site.":[84,97],"Two":[85],"models":[87],"are":[88],"presented":[89,124],"capture":[91],"topic":[93],"dependences":[94],"Then":[98],"hidden":[100],"Markov":[101],"(HMT)":[103],"model":[104,110],"utilized":[106],"statistical":[109],"tree,":[118],"an":[120,143],"HMT-based":[121],"classifier":[122],"their":[126],"classification.":[127],"Moreover,":[128],"reducing":[130],"download":[132],"size":[133],"but":[137],"still":[138],"keeping":[139],"high":[140,180],"accuracy,":[142],"entropy-based":[144],"introduced":[147],"dynamically":[149],"prune":[150],"trees.":[153],"On":[154],"these":[155],"bases,":[156],"we":[157],"employ":[158],"two-phase":[160],"system":[162],"classifying":[164],"through":[167],"fine-to-coarse":[169],"recursion.":[170],"The":[171],"experiments":[172],"show":[173],"able":[177],"offer":[179],"accuracy":[181],"efficient":[183],"process":[184],"performance.":[185]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}