{"id":"https://openalex.org/W2076008912","doi":"https://doi.org/10.1145/276304.276332","title":"Enhanced hypertext categorization using hyperlinks","display_name":"Enhanced hypertext categorization using hyperlinks","publication_year":1998,"publication_date":"1998-06-01","ids":{"openalex":"https://openalex.org/W2076008912","doi":"https://doi.org/10.1145/276304.276332","mag":"2076008912"},"language":"en","primary_location":{"id":"doi:10.1145/276304.276332","doi":"https://doi.org/10.1145/276304.276332","is_oa":true,"landing_page_url":"https://doi.org/10.1145/276304.276332","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/276304.276332","source":{"id":"https://openalex.org/S4393915683","display_name":"ACM SIGMOD International Conference on Management of Data (SIGMOD)","issn_l":"0730-8078","issn":["0730-8078"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1998 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/276304.276332","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101457009","display_name":"Soumen Chakrabarti","orcid":"https://orcid.org/0000-0002-9419-7486","observed_orcids":["https://orcid.org/0000-0002-9419-7486"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumen Chakrabarti","raw_affiliation_strings":["IBM Almaden","IBM Almaden,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden,#TAB#","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031458509","display_name":"Byron Dom","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Byron Dom","raw_affiliation_strings":["IBM Almaden","IBM Almaden,#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Almaden","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210085935"]},{"raw_affiliation_string":"IBM Almaden,#TAB#","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076056716","display_name":"Piotr Indyk","orcid":"https://orcid.org/0009-0005-2022-8429","observed_orcids":["https://orcid.org/0009-0005-2022-8429"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piotr Indyk","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":18.7949,"has_fulltext":true,"cited_by_count":766,"citation_normalized_percentile":{"value":0.99673403,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"307","last_page":"318"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9916999936103821,"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":0.9916999936103821,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.005900000222027302,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.0005000000237487257,"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/relaxation-labeling","display_name":"relaxation labeling","score":0.8930000066757202},{"id":"https://openalex.org/keywords/topic-taxonomy","display_name":"topic taxonomy","score":0.5730000138282776},{"id":"https://openalex.org/keywords/patent-classification","display_name":"patent classification","score":0.6650000214576721},{"id":"https://openalex.org/keywords/web-page-classification","display_name":"web page classification","score":0.5230000019073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8318133354187012},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6749897003173828},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.5672802925109863},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5256751179695129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5061735510826111},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.4617135524749756},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4593828320503235},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4187760651111603},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.32437774538993835},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.20025721192359924}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/276304.276332","doi":"https://doi.org/10.1145/276304.276332","is_oa":true,"landing_page_url":"https://doi.org/10.1145/276304.276332","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/276304.276332","source":{"id":"https://openalex.org/S4393915683","display_name":"ACM SIGMOD International Conference on Management of Data (SIGMOD)","issn_l":"0730-8078","issn":["0730-8078"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1998 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.49.5728","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.49.5728","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.berkeley.edu/~soumen/sigmod98.ps","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/276304.276332","doi":"https://doi.org/10.1145/276304.276332","is_oa":true,"landing_page_url":"https://doi.org/10.1145/276304.276332","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/276304.276332","source":{"id":"https://openalex.org/S4393915683","display_name":"ACM SIGMOD International Conference on Management of Data (SIGMOD)","issn_l":"0730-8078","issn":["0730-8078"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 1998 ACM SIGMOD international conference on Management of data","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2076008912.pdf","grobid_xml":"https://content.openalex.org/works/W2076008912.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W199936525","https://openalex.org/W1483135265","https://openalex.org/W1496189887","https://openalex.org/W1518603657","https://openalex.org/W1524520778","https://openalex.org/W1539441967","https://openalex.org/W1540269913","https://openalex.org/W1565117431","https://openalex.org/W1565236324","https://openalex.org/W1576962511","https://openalex.org/W1578174908","https://openalex.org/W1580192285","https://openalex.org/W1594031697","https://openalex.org/W1618527364","https://openalex.org/W1620204465","https://openalex.org/W1632778076","https://openalex.org/W1852143573","https://openalex.org/W1874629772","https://openalex.org/W1878791791","https://openalex.org/W1880604373","https://openalex.org/W1907928872","https://openalex.org/W1936761021","https://openalex.org/W1956559956","https://openalex.org/W1962539974","https://openalex.org/W1967322151","https://openalex.org/W1973610950","https://openalex.org/W1973939477","https://openalex.org/W1989393439","https://openalex.org/W1995252078","https://openalex.org/W1999138184","https://openalex.org/W2009282728","https://openalex.org/W2014901406","https://openalex.org/W2024968650","https://openalex.org/W2029373189","https://openalex.org/W2031237045","https://openalex.org/W2041706320","https://openalex.org/W2054804336","https://openalex.org/W2060458867","https://openalex.org/W2063735123","https://openalex.org/W2074676569","https://openalex.org/W2083244749","https://openalex.org/W2085908709","https://openalex.org/W2093161342","https://openalex.org/W2094934653","https://openalex.org/W2095150974","https://openalex.org/W2100838228","https://openalex.org/W2103703099","https://openalex.org/W2107792892","https://openalex.org/W2108835275","https://openalex.org/W2111313557","https://openalex.org/W2127404191","https://openalex.org/W2134094449","https://openalex.org/W2137697137","https://openalex.org/W2158292827","https://openalex.org/W2196501509","https://openalex.org/W2216176825","https://openalex.org/W2219913134","https://openalex.org/W2240733204","https://openalex.org/W2280733358","https://openalex.org/W2440833291","https://openalex.org/W3016210511","https://openalex.org/W3017143921","https://openalex.org/W4210963107","https://openalex.org/W4297957988","https://openalex.org/W6676421440"],"related_works":["https://openalex.org/W7095997837","https://openalex.org/W7098738528","https://openalex.org/W1596622341","https://openalex.org/W1482260847","https://openalex.org/W7097533226","https://openalex.org/W2110224739","https://openalex.org/W7100513285","https://openalex.org/W2393695229","https://openalex.org/W2155064424","https://openalex.org/W1472289474"],"abstract_inverted_index":{"A":[0],"major":[1],"challenge":[2],"in":[3,52,86,117,164,199],"indexing":[4],"unstructured":[5],"hypertext":[6,44,188,207,229],"databases":[7],"is":[8,38,76,80,99],"to":[9,100,128,172,204,211,233],"automatically":[10],"extract":[11],"meta-data":[12],"that":[13,64,157,186],"enables":[14],"structured":[15],"search":[16,28],"using":[17,197],"topic":[18],"taxonomies,":[19],"circumvents":[20],"keyword":[21],"ambiguity,":[22],"and":[23,29,32,105,144],"improves":[24],"the":[25,53,87,129,145,162,165,173,183,215,221],"quality":[26],"of":[27,42,84,90,131,161,182],"profile-based":[30],"routing":[31],"filtering.":[33],"Therefore,":[34],"an":[35,39],"accurate":[36],"classifier":[37,156,179,208,223,230],"essential":[40],"component":[41],"a":[43,68,91,106,118,154],"database.":[45],"Hyperlinks":[46],"pose":[47],"new":[48],"problems":[49],"not":[50],"addressed":[51],"extensive":[54],"text":[55,155,222],"classification":[56,112],"literature.":[57],"Links":[58],"clearly":[59],"contain":[60],"high-quality":[61],"semantic":[62],"clues":[63],"are":[65],"lost":[66],"upon":[67],"purely":[69],"term-based":[70],"classifier,":[71],"but":[72],"exploiting":[73,114],"link":[74,88,115],"information":[75,116],"non-trivial":[77],"because":[78],"it":[79,210],"noisy.":[81],"Naive":[82],"use":[83],"terms":[85,198],"neighborhood":[89,120],"document":[92],"can":[93,189],"even":[94],"degrade":[95],"accuracy.":[96],"Our":[97,123],"contribution":[98],"propose":[101],"robust":[102],"statistical":[103],"models":[104],"relaxation":[107],"labeling":[108],"technique":[109,124],"for":[110],"better":[111],"by":[113],"small":[119],"around":[121],"documents.":[122],"also":[125],"adapts":[126],"gracefully":[127],"fraction":[130],"neighboring":[132,200],"documents":[133,163,201],"having":[134],"known":[135],"topics.":[136],"We":[137],"experimented":[138],"with":[139,214],"pre-classified":[140],"samples":[141],"from":[142],"Yahoo!1":[143],"US":[146],"Patent":[147],"Database2.":[148],"In":[149],"previous":[150],"work,":[151],"we":[152],"developed":[153],"misclassified":[158,180],"only":[159,234],"13%":[160],"well-known":[166],"Reuters":[167],"benchmark;":[168],"this":[169,232],"was":[170],"comparable":[171],"best":[174],"results":[175],"ever":[176],"obtained.":[177],"This":[178],"36%":[181],"patents,":[184],"indicating":[185],"classifying":[187,194],"be":[190],"more":[191,219],"difficult":[192],"than":[193],"text.":[195],"Naively":[196],"increased":[202],"error":[203],"38%;":[205],"our":[206,228],"reduced":[209,231],"21%.":[212,235],"Results":[213],"Yahoo!":[216],"sample":[217],"were":[218],"dramatic:":[220],"showed":[224],"68%":[225],"error,":[226],"whereas":[227]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":24},{"year":2015,"cited_by_count":19},{"year":2014,"cited_by_count":25},{"year":2013,"cited_by_count":37},{"year":2012,"cited_by_count":46}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}
