{"id":"https://openalex.org/W2156577800","doi":"https://doi.org/10.1145/1135777.1135813","title":"Finding advertising keywords on web pages","display_name":"Finding advertising keywords on web pages","publication_year":2006,"publication_date":"2006-05-23","ids":{"openalex":"https://openalex.org/W2156577800","doi":"https://doi.org/10.1145/1135777.1135813","mag":"2156577800"},"language":"en","primary_location":{"id":"doi:10.1145/1135777.1135813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference 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/A5066873932","display_name":"Wen-tau Yih","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wen-tau Yih","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110237290","display_name":"Joshua Goodman","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joshua Goodman","raw_affiliation_strings":["Microsoft Research, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104027712","display_name":"Vitor R. Carvalho","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vitor R. Carvalho","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":33.5715,"has_fulltext":false,"cited_by_count":338,"citation_normalized_percentile":{"value":0.99785182,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9998999834060669,"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":0.9959999918937683,"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":0.975600004196167,"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/computer-science","display_name":"Computer science","score":0.8363147377967834},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6940490007400513},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6743322014808655},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6119534969329834},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4989354610443115},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.46705710887908936},{"id":"https://openalex.org/keywords/revenue","display_name":"Revenue","score":0.4279882311820984}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363147377967834},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6940490007400513},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6743322014808655},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6119534969329834},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4989354610443115},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.46705710887908936},{"id":"https://openalex.org/C195487862","wikidata":"https://www.wikidata.org/wiki/Q850210","display_name":"Revenue","level":2,"score":0.4279882311820984},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1135777.1135813","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1135777.1135813","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 15th international conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.6904","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.6904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.research.microsoft.com/~joshuago/YihGoCa-www06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W16630746","https://openalex.org/W41834883","https://openalex.org/W123239138","https://openalex.org/W1486865875","https://openalex.org/W1592796124","https://openalex.org/W1907578970","https://openalex.org/W1967766192","https://openalex.org/W1994485670","https://openalex.org/W2064418625","https://openalex.org/W2118029084","https://openalex.org/W2125055259","https://openalex.org/W2125838338","https://openalex.org/W2142340904","https://openalex.org/W2144164935","https://openalex.org/W2144578941","https://openalex.org/W2145766604","https://openalex.org/W2155925463","https://openalex.org/W2158941357","https://openalex.org/W2161290181","https://openalex.org/W2163915185","https://openalex.org/W2169150382","https://openalex.org/W2912934387","https://openalex.org/W2915429162","https://openalex.org/W2963983968","https://openalex.org/W4285719527","https://openalex.org/W6600663345","https://openalex.org/W6601685744","https://openalex.org/W6628983414","https://openalex.org/W6639689704","https://openalex.org/W6683481755"],"related_works":["https://openalex.org/W2319969327","https://openalex.org/W42295635","https://openalex.org/W1973996291","https://openalex.org/W2330575325","https://openalex.org/W2163803519","https://openalex.org/W3096145648","https://openalex.org/W3197510923","https://openalex.org/W2370579019","https://openalex.org/W3081419012","https://openalex.org/W2365267743"],"abstract_inverted_index":{"A":[0],"large":[1],"and":[2,22,82],"growing":[3],"number":[4,65],"of":[5,19,28,37,66,72,99],"web":[6,32,56],"pages":[7,57,101],"display":[8],"contextual":[9],"advertising":[10],"based":[11],"on":[12,110],"keywords":[13,54,118],"automatically":[14],"extracted":[15],"from":[16,55,119],"the":[17,20,31,35,85],"text":[18],"page,":[21],"this":[23,38,111],"is":[24,94,124],"a":[25,47,64,97],"substantial":[26],"source":[27],"revenue":[29],"supporting":[30],"today.":[33],"Despite":[34],"importance":[36],"area,":[39],"little":[40],"formal,":[41],"published":[42],"research":[43],"exists.":[44],"We":[45],"describe":[46],"system":[48,62,93],"that":[49,102],"learns":[50],"how":[51,83],"to":[52],"extract":[53,116],"for":[58],"advertisement":[59],"targeting.":[60],"The":[61,92],"uses":[63],"features,":[67],"such":[68],"as":[69],"term":[70,86],"frequency":[71],"each":[73],"potential":[74],"keyword,":[75],"inverse":[76],"document":[77],"frequency,":[78],"presence":[79],"in":[80,88],"meta-data,":[81],"often":[84],"occurs":[87],"search":[89],"query":[90],"logs.":[91],"trained":[95],"with":[96,106],"set":[98],"example":[100],"have":[103],"been":[104],"hand-labeled":[105],"\"relevant\"":[107],"keywords.":[108],"Based":[109],"training,":[112],"it":[113],"can":[114],"then":[115],"new":[117],"previously":[120],"unseen":[121],"pages.":[122],"Accuracy":[123],"substantially":[125],"better":[126],"than":[127],"several":[128],"baseline":[129],"systems.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":25},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":18},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":18},{"year":2013,"cited_by_count":28},{"year":2012,"cited_by_count":32}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}