{"id":"https://openalex.org/W2000745862","doi":"https://doi.org/10.1145/1963192.1963261","title":"Identifying primary content from web pages and its application to web search ranking","display_name":"Identifying primary content from web pages and its application to web search ranking","publication_year":2011,"publication_date":"2011-03-28","ids":{"openalex":"https://openalex.org/W2000745862","doi":"https://doi.org/10.1145/1963192.1963261","mag":"2000745862"},"language":"en","primary_location":{"id":"doi:10.1145/1963192.1963261","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963192.1963261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international conference companion on World wide web","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/A5046017610","display_name":"Srinivas Vadrevu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Srinivas Vadrevu","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028575607","display_name":"Emre Velipasaoglu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Emre Velipasaoglu","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA","Yahoo! Labs., Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo! Labs., Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046017610"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":3.0578,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.9253447,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"135","last_page":"136"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9922000169754028,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9677000045776367,"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/information-retrieval","display_name":"Information retrieval","score":0.8336819410324097},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8176054954528809},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7899688482284546},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6464508771896362},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5868412852287292},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5289029479026794},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.48990005254745483},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4848228991031647},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.4174584150314331},{"id":"https://openalex.org/keywords/backlink","display_name":"Backlink","score":0.41239726543426514},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.41036278009414673},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.19155603647232056},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10055717825889587}],"concepts":[{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8336819410324097},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8176054954528809},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7899688482284546},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6464508771896362},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5868412852287292},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5289029479026794},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.48990005254745483},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4848228991031647},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4174584150314331},{"id":"https://openalex.org/C71325787","wikidata":"https://www.wikidata.org/wiki/Q373952","display_name":"Backlink","level":5,"score":0.41239726543426514},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.41036278009414673},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.19155603647232056},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10055717825889587},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1963192.1963261","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1963192.1963261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th international conference companion on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.205.9281","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.205.9281","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2011india.com/proceeding/companion/p135.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1513638398","https://openalex.org/W1566513354","https://openalex.org/W2000569744","https://openalex.org/W2085030399","https://openalex.org/W2167859982","https://openalex.org/W4234200495"],"related_works":["https://openalex.org/W1979144454","https://openalex.org/W2069679074","https://openalex.org/W4239898202","https://openalex.org/W2552270810","https://openalex.org/W1486482441","https://openalex.org/W1998900697","https://openalex.org/W2026271528","https://openalex.org/W2031790754","https://openalex.org/W2591821839","https://openalex.org/W2048980695"],"abstract_inverted_index":{"Web":[0],"pages":[1],"are":[2],"usually":[3],"highly":[4],"structured":[5],"documents.":[6],"In":[7,25,82],"some":[8,19],"documents,":[9,27],"content":[10,88,124,133],"with":[11],"different":[12,91],"functionality":[13],"is":[14,107],"laid":[15],"out":[16],"in":[17,138],"blocks,":[18],"merely":[20],"supporting":[21],"the":[22,53,60,67,139,163],"main":[23,35],"discourse.":[24],"other":[26],"there":[28],"may":[29,76],"be":[30,98],"several":[31],"blocks":[32,65,92,117],"of":[33,52,56,66,90,93,122,149,165,178],"unrelated":[34],"content.":[36,58],"Indexing":[37],"a":[38,45,94,102,111,120,166,170,175],"web":[39,68,95,112,167],"page":[40,69,96,113,168],"as":[41,136,153,155,169],"if":[42],"it":[43,75],"were":[44],"linear":[46],"document":[47],"can":[48,97],"cause":[49],"problems":[50],"because":[51],"diverse":[54],"nature":[55],"its":[57],"If":[59],"retrieval":[61,103],"function":[62],"treats":[63,162],"all":[64],"equally":[70],"without":[71],"attention":[72],"to":[73,78,100,130,159],"structure,":[74],"lead":[77],"irrelevant":[79],"query":[80],"matches.":[81],"this":[83],"paper,":[84],"we":[85],"describe":[86,128],"how":[87,129],"quality":[89,134],"utilized":[99],"improve":[101],"function.":[104],"Our":[105],"method":[106,146],"based":[108],"on":[109],"segmenting":[110],"into":[114],"semantically":[115],"coherent":[116],"and":[118,173],"learning":[119],"predictor":[121],"segment":[123,132],"quality.":[125],"We":[126],"also":[127],"use":[131],"estimates":[135],"weights":[137],"BM25F":[140,160],"formulation.":[141],"Experimental":[142],"results":[143,151],"show":[144],"our":[145],"improves":[147],"relevance":[148],"retrieved":[150],"by":[152,174],"much":[154],"4.5":[156],"%":[157,181],"compared":[158],"that":[161],"body":[164],"single":[171],"section,":[172],"larger":[176],"margin":[177],"over":[179],"9":[180],"for":[182],"difficult":[183],"queries.":[184]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
