{"id":"https://openalex.org/W2757390321","doi":"https://doi.org/10.1145/3121050.3121083","title":"Enhanced Probabilistic Classify and Count Methods for Multi-Label Text Quantification","display_name":"Enhanced Probabilistic Classify and Count Methods for Multi-Label Text Quantification","publication_year":2017,"publication_date":"2017-09-29","ids":{"openalex":"https://openalex.org/W2757390321","doi":"https://doi.org/10.1145/3121050.3121083","mag":"2757390321"},"language":"en","primary_location":{"id":"doi:10.1145/3121050.3121083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3121050.3121083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGIR International Conference on Theory of 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/A5113825831","display_name":"Roy Levin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]},{"id":"https://openalex.org/I4210125051","display_name":"Microsoft (Israel)","ror":"https://ror.org/03819cc96","country_code":"IL","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210125051"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Roy Levin","raw_affiliation_strings":["Microsoft & IBM Research - Haifa, Herzelia, Israel"],"affiliations":[{"raw_affiliation_string":"Microsoft & IBM Research - Haifa, Herzelia, Israel","institution_ids":["https://openalex.org/I4210167297","https://openalex.org/I4210125051"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071848619","display_name":"Haggai Roitman","orcid":"https://orcid.org/0000-0002-5260-2287"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Haggai Roitman","raw_affiliation_strings":["IBM Research - Haifa, Haifa, Israel"],"affiliations":[{"raw_affiliation_string":"IBM Research - Haifa, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113825831"],"corresponding_institution_ids":["https://openalex.org/I4210125051","https://openalex.org/I4210167297"],"apc_list":null,"apc_paid":null,"fwci":0.8306,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8099193,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"229","last_page":"232"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9997000098228455,"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":0.9997000098228455,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9879000186920166,"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":0.9796000123023987,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.7389465570449829},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7282524108886719},{"id":"https://openalex.org/keywords/multi-label-classification","display_name":"Multi-label classification","score":0.6838915944099426},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6185839772224426},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6116173267364502},{"id":"https://openalex.org/keywords/cardinality","display_name":"Cardinality (data modeling)","score":0.5466426610946655},{"id":"https://openalex.org/keywords/probabilistic-classification","display_name":"Probabilistic classification","score":0.5397065877914429},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49150264263153076},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4843086302280426},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4540752172470093},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3797649145126343},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.1791103482246399},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.17353808879852295}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7389465570449829},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282524108886719},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.6838915944099426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6185839772224426},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6116173267364502},{"id":"https://openalex.org/C87117476","wikidata":"https://www.wikidata.org/wiki/Q362383","display_name":"Cardinality (data modeling)","level":2,"score":0.5466426610946655},{"id":"https://openalex.org/C189119545","wikidata":"https://www.wikidata.org/wiki/Q5128022","display_name":"Probabilistic classification","level":4,"score":0.5397065877914429},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49150264263153076},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4843086302280426},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4540752172470093},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3797649145126343},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.1791103482246399},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.17353808879852295},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3121050.3121083","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3121050.3121083","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1826790618","https://openalex.org/W1994359007","https://openalex.org/W2000484728","https://openalex.org/W2012942264","https://openalex.org/W2098824882","https://openalex.org/W2158243283","https://openalex.org/W4212863985"],"related_works":["https://openalex.org/W2615250133","https://openalex.org/W2177788029","https://openalex.org/W2516761773","https://openalex.org/W2040801326","https://openalex.org/W1957831838","https://openalex.org/W4312017181","https://openalex.org/W4385147326","https://openalex.org/W2109313498","https://openalex.org/W1998660429","https://openalex.org/W2089923511"],"abstract_inverted_index":{"In":[0],"this":[1,12],"work":[2],"we":[3,80],"address":[4],"the":[5,40,65,88,100,118],"problem":[6],"of":[7,18,39,42],"Multi-Label":[8],"Text":[9],"Quantification.":[10],"To":[11],"end,":[13],"for":[14],"a":[15,75],"given":[16],"collection":[17],"documents,":[19],"each":[20,43],"was":[21],"pre-classified":[22],"with":[23],"one":[24],"or":[25],"more":[26],"labels":[27,106],"by":[28,68,93,108],"some":[29],"multi-label":[30,77],"classifier,":[31],"our":[32,94,116],"goal":[33],"is":[34],"to":[35,99],"find":[36],"an":[37,83],"estimate":[38],"cardinality":[41],"actual":[44,101],"label":[45,90,102],"set,":[46],"as":[47,49],"accurate":[48],"possible.":[50],"We":[51],"present":[52],"two":[53],"enhanced":[54],"Probabilistic":[55],"Classify":[56],"and":[57],"Count":[58],"(PCC)":[59],"methods":[60],"that":[61,86],"focus":[62],"on":[63,82],"improving":[64],"quantification":[66,119],"accuracy":[67,120],"employing":[69],"another":[70],"supervised":[71],"learning":[72],"phase.":[73],"Using":[74],"real-world":[76],"documents":[78],"dataset,":[79],"report":[81],"experimental":[84],"evaluation":[85],"compares":[87],"estimated":[89],"counts":[91,103],"produced":[92],"solution":[95],"(and":[96],"several":[97],"alternatives)":[98],"derived":[104],"from":[105],"assigned":[107],"human":[109],"experts.":[110],"Our":[111],"results":[112],"confirm":[113],"that,":[114],"using":[115],"solution,":[117],"can":[121],"be":[122],"significantly":[123],"improved.":[124]},"counts_by_year":[{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}