{"id":"https://openalex.org/W1596622341","doi":null,"title":"Hypertext Categorization using Hyperlink Patterns and Meta Data","display_name":"Hypertext Categorization using Hyperlink Patterns and Meta Data","publication_year":2001,"publication_date":"2001-06-28","ids":{"openalex":"https://openalex.org/W1596622341","mag":"1596622341"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.8827","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.8827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~yiming/papers.yy/hypertext-icml01.ps.gz","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5081839926","display_name":"Rayid Ghani","orcid":"https://orcid.org/0000-0003-0235-1843","observed_orcids":["https://orcid.org/0000-0003-0235-1843"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rayid Ghani","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0235-1843","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086118570","display_name":"Se\u00e1n Slattery","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Se\u00e1n Slattery","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5106542734","display_name":"Yiming Yang","orcid":"https://orcid.org/0009-0006-5844-7085","observed_orcids":["https://orcid.org/0009-0006-5844-7085","https://orcid.org/0009-0001-2569-2539"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiming Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.7777,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.96541639,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"178","last_page":"185"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9789999723434448,"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":0.9789999723434448,"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":0.011699999682605267,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.006099999882280827,"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/web-page-metadata","display_name":"web page metadata","score":0.6110000014305115},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.6769999861717224},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.6610000133514404},{"id":"https://openalex.org/keywords/naive-bayes","display_name":"naive Bayes","score":0.777999997138977},{"id":"https://openalex.org/keywords/nearest-neighbors","display_name":"nearest neighbors","score":0.718999981880188},{"id":"https://openalex.org/keywords/foil","display_name":"foil","score":0.7770000100135803},{"id":"https://openalex.org/keywords/classifier-comparison","display_name":"classifier comparison","score":0.5619999766349792}],"concepts":[{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.875154972076416},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864096760749817},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.752119243144989},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7129960060119629},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4994475841522217},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43402034044265747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2740945816040039},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.10516247153282166}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.28.8827","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.28.8827","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~yiming/papers.yy/hypertext-icml01.ps.gz","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.418.3953","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.418.3953","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nyc.lti.cs.cmu.edu/yiming/Publications/rghani-icml01.pdf","raw_type":"text"},{"id":"mag:1596622341","doi":null,"is_oa":false,"landing_page_url":"http://portal.acm.org/citation.cfm?id=658307","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7100513285","https://openalex.org/W1482260847","https://openalex.org/W3015720892","https://openalex.org/W2155064424","https://openalex.org/W7095997837","https://openalex.org/W1608305107","https://openalex.org/W67510309","https://openalex.org/W1580305312","https://openalex.org/W7097533226","https://openalex.org/W7098738528"],"abstract_inverted_index":{"Hypertext":[0],"poses":[1],"new":[2],"text":[3,35],"classification":[4,28,149],"research":[5],"challenges":[6],"as":[7],"hyperlinks,":[8],"content":[9],"of":[10,24,41,51,77,84,155,169],"linked":[11,97,107],"documents,":[12],"and":[13,48,58,112,167],"meta":[14,129],"data":[15,130],"about":[16],"related":[17],"web":[18,46,70],"sites":[19],"all":[20],"provide":[21],"richer":[22],"sources":[23,83],"information":[25,43,85],"for":[26,44,147,172],"hypertext":[27,173],"that":[29,66,96,113,128],"are":[30,109],"not":[31],"available":[32],"in":[33,60,69,119],"traditional":[34],"classification.":[36,174],"We":[37,64],"investigate":[38],"the":[39,49,90,106,152,156,165],"use":[40],"such":[42],"representing":[45],"sites,":[47],"effectiveness":[50],"different":[52,157],"classifiers":[53,158],"(Naive":[54],"Bayes,":[55],"Nearest":[56],"Neighbor,":[57],"Foil)":[59],"exploiting":[61,81],"those":[62],"representations.":[63],"find":[65],"using":[67,139],"words":[68],"pages":[71,98],"alone":[72],"often":[73,133],"yields":[74],"suboptimal":[75],"performance":[76,154],"classifiers,":[78],"compared":[79],"to":[80,116],"additional":[82],"beyond":[86],"document":[87],"content.":[88],"On":[89],"other":[91],"hand,":[92],"we":[93],"also":[94],"observe":[95],"can":[99,136,143],"be":[100,117,137,144],"more":[101],"harmful":[102],"than":[103],"helpful":[104],"when":[105],"neighborhoods":[108],"highly":[110],"\"noisy\"":[111],"links":[114],"have":[115],"used":[118],"a":[120],"careful":[121],"manner.":[122],"More":[123],"importantly,":[124],"our":[125,170],"investigation":[126],"suggests":[127],"which":[131],"is":[132],"available,":[134],"or":[135],"acquired":[138],"Information":[140],"Extraction":[141],"techniques,":[142],"extremely":[145],"useful":[146],"improving":[148],"accuracy.":[150],"Finally,":[151],"relative":[153],"being":[159],"tested":[160],"gives":[161],"us":[162],"insights":[163],"into":[164],"strengths":[166],"limitations":[168],"algorithms":[171],"1.":[175]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":7}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}