{"id":"https://openalex.org/W2171710828","doi":"https://doi.org/10.1145/1571941.1571982","title":"Using anchor texts with their hyperlink structure for web search","display_name":"Using anchor texts with their hyperlink structure for web search","publication_year":2009,"publication_date":"2009-07-19","ids":{"openalex":"https://openalex.org/W2171710828","doi":"https://doi.org/10.1145/1571941.1571982","mag":"2171710828"},"language":"en","primary_location":{"id":"doi:10.1145/1571941.1571982","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1571982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","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/A5010558184","display_name":"Zhicheng Dou","orcid":"https://orcid.org/0000-0002-9781-948X"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhicheng Dou","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101505570","display_name":"Ruihua Song","orcid":"https://orcid.org/0000-0001-6036-9035"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihua Song","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018977183","display_name":"Jian\u2010Yun Nie","orcid":"https://orcid.org/0000-0003-1556-3335"},"institutions":[{"id":"https://openalex.org/I70931966","display_name":"Universit\u00e9 de Montr\u00e9al","ror":"https://ror.org/0161xgx34","country_code":"CA","type":"education","lineage":["https://openalex.org/I70931966"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jian-Yun Nie","raw_affiliation_strings":["University of Montreal, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"University of Montreal, Montreal, Canada","institution_ids":["https://openalex.org/I70931966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5010558184"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":11.6445,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.98320915,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"227","last_page":"234"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9975000023841858,"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":0.9962999820709229,"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/hyperlink","display_name":"Hyperlink","score":0.9400755763053894},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7531311511993408},{"id":"https://openalex.org/keywords/complement","display_name":"Complement (music)","score":0.7410378456115723},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6440989971160889},{"id":"https://openalex.org/keywords/web-site","display_name":"Web site","score":0.6025568246841431},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5668363571166992},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4997222423553467},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.48212599754333496},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.44312217831611633},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4161131978034973},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.23668506741523743},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10215404629707336}],"concepts":[{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.9400755763053894},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7531311511993408},{"id":"https://openalex.org/C112313634","wikidata":"https://www.wikidata.org/wiki/Q7886648","display_name":"Complement (music)","level":5,"score":0.7410378456115723},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6440989971160889},{"id":"https://openalex.org/C2984519610","wikidata":"https://www.wikidata.org/wiki/Q35127","display_name":"Web site","level":3,"score":0.6025568246841431},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5668363571166992},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4997222423553467},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.48212599754333496},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.44312217831611633},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4161131978034973},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.23668506741523743},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10215404629707336},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127716648","wikidata":"https://www.wikidata.org/wiki/Q104053","display_name":"Phenotype","level":3,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C188082640","wikidata":"https://www.wikidata.org/wiki/Q1780899","display_name":"Complementation","level":4,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1571941.1571982","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1571982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.9467","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.9467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/pubs/80581/sigirfp185-dou.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W155984473","https://openalex.org/W1482214997","https://openalex.org/W1828972360","https://openalex.org/W1978394996","https://openalex.org/W1985554184","https://openalex.org/W2012057220","https://openalex.org/W2066636486","https://openalex.org/W2085030399","https://openalex.org/W2086511124","https://openalex.org/W2091808810","https://openalex.org/W2093390569","https://openalex.org/W2094154703","https://openalex.org/W2124658502","https://openalex.org/W2138621811","https://openalex.org/W2143331230","https://openalex.org/W2147872511","https://openalex.org/W2156037541","https://openalex.org/W2164052363","https://openalex.org/W2171161922","https://openalex.org/W4206765718","https://openalex.org/W4251560691"],"related_works":["https://openalex.org/W2384033143","https://openalex.org/W2245616560","https://openalex.org/W2351804282","https://openalex.org/W2048998278","https://openalex.org/W1556894713","https://openalex.org/W158130761","https://openalex.org/W1490416172","https://openalex.org/W2588706232","https://openalex.org/W2096877906","https://openalex.org/W2084041205"],"abstract_inverted_index":{"As":[0],"a":[1],"good":[2],"complement":[3],"to":[4,15,28,67,97],"page":[5],"content,":[6],"anchor":[7,23,43,75,99],"texts":[8,24,100],"have":[9,25],"been":[10,26],"extensively":[11],"used,":[12],"and":[13,89],"proven":[14],"be":[16,29,50],"useful,":[17],"in":[18,81,101],"commercial":[19],"search":[20],"engines.":[21],"However,":[22],"assumed":[27],"independent,":[30],"whether":[31],"they":[32],"come":[33],"from":[34,45,57,85,91],"the":[35,58,71,86,98,116],"same":[36,59,87],"Web":[37,47],"site":[38,88],"or":[39],"not.":[40],"Intuitively,":[41],"an":[42],"text":[44],"unrelated":[46],"sites":[48],"should":[49],"considered":[51],"as":[52],"stronger":[53],"evidence":[54],"than":[55],"that":[56,110],"site.":[60],"This":[61],"paper":[62],"proposes":[63],"two":[64,79,103,112],"new":[65,113],"methods":[66],"take":[68],"into":[69],"account":[70],"possible":[72],"relationships":[73,80],"between":[74,122],"texts.":[76],"We":[77],"consider":[78],"this":[82],"paper:":[83],"links":[84,90],"related":[92],"sites.":[93],"The":[94],"importance":[95],"assigned":[96],"these":[102,111],"situations":[104],"is":[105],"discounted.":[106],"Experimental":[107],"results":[108],"show":[109],"models":[114],"outperform":[115],"baseline":[117],"model":[118],"which":[119],"assumes":[120],"independence":[121],"hyperlinks.":[123]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
