{"id":"https://openalex.org/W2156996965","doi":"https://doi.org/10.1145/1772690.1772771","title":"A large-scale active learning system for topical categorization on the web","display_name":"A large-scale active learning system for topical categorization on the web","publication_year":2010,"publication_date":"2010-04-26","ids":{"openalex":"https://openalex.org/W2156996965","doi":"https://doi.org/10.1145/1772690.1772771","mag":"2156996965"},"language":"en","primary_location":{"id":"doi:10.1145/1772690.1772771","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th 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/A5019655341","display_name":"Suju Rajan","orcid":"https://orcid.org/0009-0003-0852-989X"},"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":"Suju Rajan","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065508800","display_name":"Dragomir Yankov","orcid":"https://orcid.org/0009-0006-4509-3222"},"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":"Dragomir Yankov","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041221603","display_name":"Scott Gaffney","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":"Scott J. Gaffney","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057069732","display_name":"Adwait Ratnaparkhi","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":"Adwait Ratnaparkhi","raw_affiliation_strings":["Yahoo! Labs, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019655341"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":4.1805,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.94266711,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"791","last_page":"800"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.9990000128746033,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9990000128746033,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9959999918937683,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9918000102043152,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7946362495422363},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.788965106010437},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5987766981124878},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5553803443908691},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5207650065422058},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5162291526794434},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5063678026199341},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5062059760093689},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.48230600357055664},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3756071925163269},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.30243998765945435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07189023494720459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7946362495422363},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.788965106010437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5987766981124878},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5553803443908691},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5207650065422058},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5162291526794434},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5063678026199341},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5062059760093689},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.48230600357055664},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3756071925163269},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30243998765945435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07189023494720459},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1772690.1772771","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772771","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.332.9226","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.332.9226","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ideal.ece.utexas.edu/~rsuju/www10.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W202303397","https://openalex.org/W1514707997","https://openalex.org/W1548614216","https://openalex.org/W1549887922","https://openalex.org/W1550206324","https://openalex.org/W1588282782","https://openalex.org/W1599263113","https://openalex.org/W1845402413","https://openalex.org/W1976526581","https://openalex.org/W1986383870","https://openalex.org/W2012331068","https://openalex.org/W2012942264","https://openalex.org/W2058732827","https://openalex.org/W2077137640","https://openalex.org/W2099550922","https://openalex.org/W2118585731","https://openalex.org/W2119157339","https://openalex.org/W2123958887","https://openalex.org/W2125055259","https://openalex.org/W2139212933","https://openalex.org/W2143534004","https://openalex.org/W2145001205","https://openalex.org/W2147896987","https://openalex.org/W2148143831","https://openalex.org/W2149684865","https://openalex.org/W2152893555","https://openalex.org/W2164943005","https://openalex.org/W2165966284","https://openalex.org/W2169075655","https://openalex.org/W2426031434","https://openalex.org/W2616657226","https://openalex.org/W3001645704","https://openalex.org/W3007702476","https://openalex.org/W3193477162","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"Many":[0],"web":[1],"applications":[2],"such":[3],"as":[4],"ad":[5],"matching":[6],"systems,":[7],"vertical":[8],"search":[9],"engines,":[10],"and":[11,32,72,109,124],"page":[12],"categorization":[13,115],"systems":[14],"require":[15],"the":[16,27,35,38,42,50],"identification":[17],"of":[18,24,34,44,49,52,75],"a":[19,46,60,68,85,94,105,118],"particular":[20],"type":[21],"or":[22],"class":[23,51],"pages":[25,36],"on":[26,37,102],"Web.":[28],"The":[29,98],"sheer":[30],"number":[31],"diversity":[33],"Web,":[39],"however,":[40],"makes":[41,73],"problem":[43],"obtaining":[45],"good":[47,95],"sample":[48,71],"interest":[53],"hard.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58],"describe":[59],"successfully":[61],"deployed":[62],"end-to-end":[63],"system":[64,99],"that":[65],"starts":[66],"from":[67,104],"biased":[69],"training":[70],"use":[74],"several":[76],"state-of-the-art":[77],"machine":[78],"learning":[79,88],"algorithms":[80],"working":[81],"in":[82,90,121],"tandem,":[83],"including":[84],"powerful":[86],"active":[87],"component,":[89],"order":[91],"to":[92,112],"achieve":[93,113],"classification":[96],"system.":[97],"is":[100,110],"evaluated":[101],"traffic":[103],"real-world":[106],"ad-matching":[107],"platform":[108],"shown":[111],"high":[114],"effectiveness":[116],"with":[117],"significant":[119],"reduction":[120],"editorial":[122],"effort":[123],"labeling":[125],"time.":[126]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
