{"id":"https://openalex.org/W2010526612","doi":"https://doi.org/10.1145/1148170.1148255","title":"Constructing informative prior distributions from domain knowledge in text classification","display_name":"Constructing informative prior distributions from domain knowledge in text classification","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2010526612","doi":"https://doi.org/10.1145/1148170.1148255","mag":"2010526612"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148255","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual 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/A5083269761","display_name":"Aynur A. Dayanik","orcid":null},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Aynur Dayanik","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020081385","display_name":"David Lewis","orcid":"https://orcid.org/0000-0002-3503-4644"},"institutions":[{"id":"https://openalex.org/I4210148173","display_name":"Morgan, Lewis & Bockius (United States)","ror":"https://ror.org/04c0z3e83","country_code":"US","type":"company","lineage":["https://openalex.org/I4210148173"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David D. Lewis","raw_affiliation_strings":["David D. Lewis Consulting, Chicago, IL"],"affiliations":[{"raw_affiliation_string":"David D. Lewis Consulting, Chicago, IL","institution_ids":["https://openalex.org/I4210148173"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018667469","display_name":"David Madigan","orcid":"https://orcid.org/0000-0001-9754-1011"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Madigan","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015430304","display_name":"Vladimir Me\u00f1kov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vladimir Menkov","raw_affiliation_strings":["Aqsaqal Enterprises, Penticton, B.C. Canada"],"affiliations":[{"raw_affiliation_string":"Aqsaqal Enterprises, Penticton, B.C. Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082142377","display_name":"Alexander Genkin","orcid":"https://orcid.org/0000-0002-0716-1304"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexander Genkin","raw_affiliation_strings":["Rutgers University, Piscataway, NJ"],"affiliations":[{"raw_affiliation_string":"Rutgers University, Piscataway, NJ","institution_ids":["https://openalex.org/I102322142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5083269761"],"corresponding_institution_ids":["https://openalex.org/I102322142"],"apc_list":null,"apc_paid":null,"fwci":11.7473,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.98483911,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"493","last_page":"500"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994000196456909,"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":0.9994000196456909,"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/T10028","display_name":"Topic Modeling","score":0.9890999794006348,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.986299991607666,"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":0.7395976781845093},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5396552085876465},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5067985653877258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4826936721801758},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.46282798051834106},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3751963973045349},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12591224908828735}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7395976781845093},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5396552085876465},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5067985653877258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4826936721801758},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.46282798051834106},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3751963973045349},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12591224908828735},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1148170.1148255","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148255","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8100000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W103965747","https://openalex.org/W173851765","https://openalex.org/W202303397","https://openalex.org/W265767496","https://openalex.org/W1494853941","https://openalex.org/W1524688041","https://openalex.org/W1540550673","https://openalex.org/W1543155826","https://openalex.org/W1557757161","https://openalex.org/W1571969069","https://openalex.org/W1604792744","https://openalex.org/W1635111378","https://openalex.org/W1638608766","https://openalex.org/W1956559956","https://openalex.org/W1970945111","https://openalex.org/W1978394996","https://openalex.org/W1993644118","https://openalex.org/W2011675537","https://openalex.org/W2020818097","https://openalex.org/W2058982198","https://openalex.org/W2074650777","https://openalex.org/W2098162425","https://openalex.org/W2109055008","https://openalex.org/W2109679423","https://openalex.org/W2118020653","https://openalex.org/W2123273303","https://openalex.org/W2135046866","https://openalex.org/W2149684865","https://openalex.org/W2150102617","https://openalex.org/W2166183437","https://openalex.org/W2325227998","https://openalex.org/W2560744859","https://openalex.org/W2612120747","https://openalex.org/W4242379934","https://openalex.org/W4285719527","https://openalex.org/W6640862754"],"related_works":["https://openalex.org/W2357241418","https://openalex.org/W2789919619","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2115485936","https://openalex.org/W2293457016","https://openalex.org/W2568140311","https://openalex.org/W4287636191","https://openalex.org/W3093553144","https://openalex.org/W1727868"],"abstract_inverted_index":{"Supervised":[0],"learning":[1,24],"approaches":[2],"to":[3,11,22,28,47,68,91,110],"text":[4,44,127],"classification":[5],"are":[6,45],"in":[7,83],"practice":[8],"often":[9],"required":[10],"work":[12],"with":[13,80],"small":[14],"and":[15,62,64,104],"unsystematically":[16],"collected":[17],"training":[18,81,106,142],"sets.":[19],"The":[20],"alternative":[21],"supervised":[23],"is":[25,53,89,108],"usually":[26],"viewed":[27],"be":[29,139],"building":[30],"classifiers":[31],"by":[32],"hand,":[33],"using":[34],"a":[35,56,84,93,100,112],"domain":[36,78],"expert's":[37],"understanding":[38],"of":[39,42,50,58,71,99],"which":[40],"features":[41],"the":[43,48,97,120],"related":[46],"class":[49],"interest.":[51],"This":[52],"expensive,":[54],"requires":[55],"degree":[57],"sophistication":[59],"about":[60],"linguistics":[61],"classification,":[63],"makes":[65],"it":[66],"difficult":[67],"use":[69],"combinations":[70],"weak":[72],"predictors.":[73],"We":[74,123],"propose":[75],"instead":[76],"combining":[77],"knowledge":[79,88],"examples":[82],"Bayesian":[85],"framework.":[86],"Domain":[87],"used":[90,109],"specify":[92],"prior":[94],"distribution":[95],"for":[96],"parameters":[98],"logistic":[101],"regression":[102],"model,":[103],"labeled":[105],"data":[107,129],"produce":[111],"posterior":[113],"distribution,":[114],"whose":[115],"mode":[116],"we":[117],"take":[118],"as":[119],"final":[121],"classifier.":[122],"show":[124],"on":[125],"three":[126],"categorization":[128],"sets":[130],"that":[131],"this":[132],"approach":[133],"can":[134],"rescue":[135],"what":[136],"would":[137],"otherwise":[138],"disastrously":[140],"bad":[141],"situations,":[143],"producing":[144],"much":[145],"more":[146],"effective":[147],"classifiers.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":3}],"updated_date":"2026-01-19T04:01:09.351973","created_date":"2025-10-10T00:00:00"}