{"id":"https://openalex.org/W2131840460","doi":"https://doi.org/10.1145/1183614.1183648","title":"Effective and efficient classification on a search-engine model","display_name":"Effective and efficient classification on a search-engine model","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2131840460","doi":"https://doi.org/10.1145/1183614.1183648","mag":"2131840460"},"language":"en","primary_location":{"id":"doi:10.1145/1183614.1183648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183648","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 ACM international conference on Information and knowledge management  - CIKM '06","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/A5000949710","display_name":"Aris Anagnostopoulos","orcid":"https://orcid.org/0000-0001-9183-7911"},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"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":["GB","US"],"is_corresponding":true,"raw_author_name":"Aris Anagnostopoulos","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA","Yahoo Research, Sunnyvale, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo Research, Sunnyvale, CA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108541542","display_name":"Andrei Broder","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]},{"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":["GB","US"],"is_corresponding":false,"raw_author_name":"Andrei Z. Broder","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA","Yahoo Research, Sunnyvale, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]},{"raw_affiliation_string":"Yahoo Research, Sunnyvale, CA#TAB#","institution_ids":["https://openalex.org/I1325784139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089487172","display_name":"Kunal Punera","orcid":null},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kunal Punera","raw_affiliation_strings":["University of Texas at Austin, Austin, TX","Univ. of Texas at Austin, Austin TX"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, TX","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Univ. of Texas at Austin, Austin TX","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5000949710"],"corresponding_institution_ids":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":2.2587,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.89364463,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"208","last_page":"208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9965999722480774,"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":0.9965999722480774,"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":0.9954000115394592,"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":0.994700014591217,"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":0.6397826671600342},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5597662329673767},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38571807742118835},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3411230444908142}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6397826671600342},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5597662329673767},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38571807742118835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3411230444908142}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1183614.1183648","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183614.1183648","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 ACM international conference on Information and knowledge management  - CIKM '06","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma1.it:11573/332443","is_oa":false,"landing_page_url":"http://hdl.handle.net/11573/332443","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W49486804","https://openalex.org/W55312212","https://openalex.org/W1482214997","https://openalex.org/W1550206324","https://openalex.org/W1570978137","https://openalex.org/W1660390307","https://openalex.org/W1840338487","https://openalex.org/W1886681306","https://openalex.org/W2005422315","https://openalex.org/W2009716188","https://openalex.org/W2025016813","https://openalex.org/W2043909051","https://openalex.org/W2098162425","https://openalex.org/W2125055259","https://openalex.org/W2126631147","https://openalex.org/W2133864802","https://openalex.org/W2134865635","https://openalex.org/W2140785063","https://openalex.org/W2149684865","https://openalex.org/W2150102617","https://openalex.org/W2154610494","https://openalex.org/W2156909104","https://openalex.org/W2164547069","https://openalex.org/W2167075392","https://openalex.org/W2435251607"],"related_works":["https://openalex.org/W167737004","https://openalex.org/W1964038241","https://openalex.org/W2185038817","https://openalex.org/W2004064649","https://openalex.org/W2385957133","https://openalex.org/W3590553","https://openalex.org/W1988452794","https://openalex.org/W2153030345","https://openalex.org/W3141094475","https://openalex.org/W2390285850"],"abstract_inverted_index":{"Traditional":[0],"document":[1,11,23,81],"classification":[2,35,95],"frameworks,":[3],"which":[4],"apply":[5],"the":[6,26,34,46,59,74,118,132,143,151,154,172,192],"learned":[7],"classifier":[8,157],"to":[9,54,72,165,169],"each":[10],"in":[12],"a":[13,38,63,80,167,178],"corpus":[14,39],"one":[15],"by":[16,105,123],"one,":[17],"are":[18,163],"infeasible":[19],"for":[20,45],"extremely":[21],"large":[22,29,64,88],"corpora,":[24],"like":[25],"Web":[27],"or":[28],"corporate":[30],"intranets.":[31],"We":[32,90],"consider":[33],"problem":[36],"on":[37,100,140],"that":[40,78,92,116,139,182],"has":[41],"been":[42],"processed":[43],"primarily":[44],"purpose":[47],"of":[48,62,120,126,150,153,171],"searching,":[49],"and":[50,160],"thus":[51],"our":[52,141],"access":[53],"documents":[55],"is":[56,71],"solely":[57],"through":[58],"inverted":[60],"index":[61],"scale":[65],"search":[66],"engine.":[67],"Our":[68],"main":[69],"goal":[70],"build":[73,177],"\"best\"":[75],"short":[76],"query":[77,121,133,147,181],"characterizes":[79],"class":[82],"using":[83],"operators":[84],"normally":[85],"available":[86],"within":[87],"engines.":[89],"show":[91,115,138],"surprisingly":[93],"good":[94],"accuracy":[96,152],"can":[97,129,176,183],"be":[98,184],"achieved":[99],"average":[101],"over":[102],"multiple":[103],"classes":[104],"queries":[106],"with":[107],"as":[108,110,189,191],"few":[109],"10":[111,145,179,194],"terms.":[112],"Moreover,":[113],"we":[114,137,162,175],"optimizing":[117],"efficiency":[119],"execution":[122],"careful":[124],"selection":[125],"these":[127],"terms":[128,146,180,195],"further":[130],"reduce":[131],"costs.":[134],"More":[135],"precisely,":[136],"set-up":[142],"best":[144,155,173,193],"canachieve":[148],"90%":[149],"SVM":[156],"(14000":[158],"terms),":[159],"if":[161],"willing":[164],"tolerate":[166],"reduction":[168],"86%":[170],"SVM,":[174],"executed":[185],"more":[186],"than":[187],"twice":[188],"fast":[190],"query.":[196]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}