{"id":"https://openalex.org/W2007278710","doi":"https://doi.org/10.1145/846183.846187","title":"Data mining for hypertext: a tutorial survey","display_name":"Data mining for hypertext: a tutorial survey","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W2007278710","doi":"https://doi.org/10.1145/846183.846187","mag":"2007278710"},"language":"en","primary_location":{"id":"doi:10.1145/846183.846187","doi":"https://doi.org/10.1145/846183.846187","is_oa":true,"landing_page_url":"https://doi.org/10.1145/846183.846187","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/846183.846187","source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/846183.846187","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/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Soumen Chakrabarti","raw_affiliation_strings":["Indian Institute of Technology Bombay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology Bombay","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101457009"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":25.2269,"has_fulltext":true,"cited_by_count":291,"citation_normalized_percentile":{"value":0.99469087,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"1","issue":"2","first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9761000275611877,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9761000275611877,"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":0.01850000023841858,"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/T14435","display_name":"Information Retrieval and Data Mining","score":0.002099999925121665,"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/world-wide-web","display_name":"World Wide Web","score":0.9309999942779541},{"id":"https://openalex.org/keywords/information-search","display_name":"information search","score":0.7279999852180481},{"id":"https://openalex.org/keywords/link-analysis","display_name":"link analysis","score":0.5799999833106995},{"id":"https://openalex.org/keywords/keyword-queries","display_name":"keyword queries","score":0.6200000047683716},{"id":"https://openalex.org/keywords/information-needs","display_name":"information needs","score":0.7300000190734863},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"supervised learning","score":0.7429999709129333},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"semi-supervised learning","score":1.0},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.9919999837875366},{"id":"https://openalex.org/keywords/web-mining","display_name":"web mining","score":0.35600000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8396737575531006},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.7938376665115356},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.6727463006973267},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.6573498249053955},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5153343081474304},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5005197525024414},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.49907875061035156},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.4833614230155945},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45771920680999756},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44471338391304016},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4432356059551239},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.37543541193008423},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.24605873227119446},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/846183.846187","doi":"https://doi.org/10.1145/846183.846187","is_oa":true,"landing_page_url":"https://doi.org/10.1145/846183.846187","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/846183.846187","source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.107.5476","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.107.5476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.dsi.unive.it/~dm/survey.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.34.4297","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.34.4297","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/doc/kddexp2000/survey.ps","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/846183.846187","doi":"https://doi.org/10.1145/846183.846187","is_oa":true,"landing_page_url":"https://doi.org/10.1145/846183.846187","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/846183.846187","source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","norway-1","vabb-shw"],"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2007278710.pdf","grobid_xml":"https://content.openalex.org/works/W2007278710.grobid-xml"},"referenced_works_count":75,"referenced_works":["https://openalex.org/W202303397","https://openalex.org/W950821216","https://openalex.org/W1485536830","https://openalex.org/W1489992655","https://openalex.org/W1493596129","https://openalex.org/W1495949396","https://openalex.org/W1516146643","https://openalex.org/W1518603657","https://openalex.org/W1523437924","https://openalex.org/W1523949738","https://openalex.org/W1537925493","https://openalex.org/W1549026077","https://openalex.org/W1550206324","https://openalex.org/W1564978311","https://openalex.org/W1570542661","https://openalex.org/W1576520375","https://openalex.org/W1598062678","https://openalex.org/W1602659231","https://openalex.org/W1605217017","https://openalex.org/W1608864735","https://openalex.org/W1620204465","https://openalex.org/W1644866298","https://openalex.org/W1659541576","https://openalex.org/W1840338487","https://openalex.org/W1849729440","https://openalex.org/W1956559956","https://openalex.org/W1971784203","https://openalex.org/W1971788485","https://openalex.org/W1972466956","https://openalex.org/W1976232673","https://openalex.org/W1977001629","https://openalex.org/W1977496278","https://openalex.org/W1981202432","https://openalex.org/W1981276685","https://openalex.org/W1987777228","https://openalex.org/W1995252078","https://openalex.org/W1996764654","https://openalex.org/W1997841190","https://openalex.org/W1998102571","https://openalex.org/W2006119904","https://openalex.org/W2008375984","https://openalex.org/W2023695725","https://openalex.org/W2040058125","https://openalex.org/W2049633694","https://openalex.org/W2062083887","https://openalex.org/W2063392856","https://openalex.org/W2066636486","https://openalex.org/W2076008912","https://openalex.org/W2079672501","https://openalex.org/W2082751088","https://openalex.org/W2092850018","https://openalex.org/W2099111195","https://openalex.org/W2100674109","https://openalex.org/W2104967207","https://openalex.org/W2111964406","https://openalex.org/W2123737232","https://openalex.org/W2126631147","https://openalex.org/W2140785063","https://openalex.org/W2147152072","https://openalex.org/W2156093156","https://openalex.org/W2164641162","https://openalex.org/W2166103330","https://openalex.org/W2196501509","https://openalex.org/W2215091624","https://openalex.org/W2333719312","https://openalex.org/W2435251607","https://openalex.org/W2562755098","https://openalex.org/W2607336911","https://openalex.org/W2794358369","https://openalex.org/W2798909945","https://openalex.org/W3017143921","https://openalex.org/W3147635348","https://openalex.org/W4240407914","https://openalex.org/W4241122026","https://openalex.org/W4256525033"],"related_works":["https://openalex.org/W7098996059","https://openalex.org/W1978748463","https://openalex.org/W1579557950","https://openalex.org/W2005677600","https://openalex.org/W7096717532","https://openalex.org/W2206513607","https://openalex.org/W4233556595","https://openalex.org/W1605694897","https://openalex.org/W2068863058","https://openalex.org/W2000325668"],"abstract_inverted_index":{"With":[0],"over":[1],"800":[2],"million":[3],"pages":[4],"covering":[5],"most":[6],"areas":[7,152],"of":[8,29,119,145,153],"human":[9],"endeavor,":[10],"the":[11,27,36,110,117,128,136,143,150],"World-wide":[12],"Web":[13,33,37,111],"is":[14,52,59],"a":[15,24,69],"fertile":[16],"ground":[17],"for":[18,61],"data":[19,133,140,146],"mining":[20,80,102,134,141],"research":[21],"to":[22,26,87,105,121,123],"make":[23],"difference":[25],"effectiveness":[28],"information":[30,64],"search.":[31],"Today,":[32],"surfers":[34],"access":[35],"through":[38],"two":[39],"dominant":[40],"interfaces:":[41],"clicking":[42],"on":[43],"hyperlinks":[44],"and":[45,55,66,81,101,109,148,155],"searching":[46],"via":[47],"keyword":[48],"queries.":[49],"This":[50],"process":[51],"often":[53],"tentative":[54],"unsatisfactory.":[56],"Better":[57],"support":[58],"needed":[60],"expressing":[62],"one's":[63],"need":[65],"dealing":[67],"with":[68],"search":[70],"result":[71],"in":[72,99,107,112,135,142],"more":[73],"structured":[74],"ways":[75],"than":[76],"available":[77],"now.":[78],"Data":[79],"machine":[82],"learning":[83,100,125],"have":[84],"significant":[85],"roles":[86],"play":[88],"towards":[89],"this":[90,92],"end.In":[91],"paper":[93],"we":[94],"will":[95,115],"survey":[96],"recent":[97,154],"advances":[98],"problems":[103],"related":[104],"hypertext":[106,137],"general":[108],"particular.":[113],"We":[114],"review":[116],"continuum":[118],"supervised":[120],"semi-supervised":[122],"unsupervised":[124],"problems,":[126],"highlight":[127],"specific":[129],"challenges":[130],"which":[131],"distinguish":[132],"domain":[138],"from":[139],"context":[144],"warehouses,":[147],"summarize":[149],"key":[151],"ongoing":[156],"research.":[157]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":14}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}
