{"id":"https://openalex.org/W2164967910","doi":"https://doi.org/10.1109/tkde.2012.148","title":"On the Use of Side Information for Mining Text Data","display_name":"On the Use of Side Information for Mining Text Data","publication_year":2012,"publication_date":"2012-08-22","ids":{"openalex":"https://openalex.org/W2164967910","doi":"https://doi.org/10.1109/tkde.2012.148","mag":"2164967910"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2012.148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2012.148","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-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/A5028089542","display_name":"Char\u0173 C. Aggarwal","orcid":"https://orcid.org/0000-0003-2579-7581"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Charu C. Aggarwal","raw_affiliation_strings":["Department of Computer Science, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, IBM T. J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087513337","display_name":"Yuchen Zhao","orcid":"https://orcid.org/0000-0003-4780-093X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuchen Zhao","raw_affiliation_strings":["Sumo Logic Inc, Redwood City, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sumo Logic Inc, Redwood City, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Chicago, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.4795,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.93020228,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"26","issue":"6","first_page":"1415","last_page":"1429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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":0.9984999895095825,"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/T11106","display_name":"Data Management and Algorithms","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9973999857902527,"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":0.8724151253700256},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7235208749771118},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6477997303009033},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5922247171401978},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.49693039059638977},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46380236744880676},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4467787444591522},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.44184258580207825},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3009014129638672},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25844115018844604}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8724151253700256},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7235208749771118},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6477997303009033},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5922247171401978},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.49693039059638977},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46380236744880676},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4467787444591522},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.44184258580207825},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3009014129638672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25844115018844604},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2012.148","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2012.148","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337370","display_name":"Office of International Science and Engineering","ror":"https://ror.org/01k638r21"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W33276683","https://openalex.org/W170573592","https://openalex.org/W316065036","https://openalex.org/W631140850","https://openalex.org/W1509894598","https://openalex.org/W1533841329","https://openalex.org/W1575476631","https://openalex.org/W1651093245","https://openalex.org/W1826790618","https://openalex.org/W1839870583","https://openalex.org/W1925932413","https://openalex.org/W1956559956","https://openalex.org/W1958077162","https://openalex.org/W1971784203","https://openalex.org/W1996764654","https://openalex.org/W1997623609","https://openalex.org/W2008244516","https://openalex.org/W2013029404","https://openalex.org/W2014615172","https://openalex.org/W2040058125","https://openalex.org/W2057712948","https://openalex.org/W2092957858","https://openalex.org/W2095897464","https://openalex.org/W2106545428","https://openalex.org/W2116237179","https://openalex.org/W2118020653","https://openalex.org/W2123549998","https://openalex.org/W2131687179","https://openalex.org/W2133576408","https://openalex.org/W2140785063","https://openalex.org/W2140809065","https://openalex.org/W2150461699","https://openalex.org/W2165515835","https://openalex.org/W2166914830","https://openalex.org/W2167036382","https://openalex.org/W2216446631","https://openalex.org/W2319660501","https://openalex.org/W2325227998","https://openalex.org/W2434205482","https://openalex.org/W4236122429","https://openalex.org/W4241122026","https://openalex.org/W4250619709","https://openalex.org/W4255387915","https://openalex.org/W4285719527","https://openalex.org/W6634394891","https://openalex.org/W6637231022","https://openalex.org/W6677504887","https://openalex.org/W6678337573"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2494523064","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W2387982377"],"abstract_inverted_index":{"In":[0,78,135],"many":[1],"text":[2,11,44],"mining":[3,90,104,122],"applications,":[4],"side-information":[5,14,64,87],"is":[6,76],"available":[7],"along":[8],"with":[9,147],"the":[10,25,28,43,59,74,89,97,100,103,111,121,128,164,167,185],"documents.":[12],"Such":[13,46],"may":[15,48,65],"be":[16,66,83],"of":[17,53,62,73,99,177,187],"different":[18],"kinds,":[19],"such":[20,79,189],"as":[21,125],"document":[22],"provenance":[23],"information,":[24],"links":[26],"in":[27,150,181],"document,":[29],"user-access":[30],"behavior":[31],"from":[32,130],"web":[33],"logs,":[34],"or":[35,106],"other":[36],"non-textual":[37],"attributes":[38,47],"which":[39,142],"are":[40],"embedded":[41],"into":[42,88],"document.":[45],"contain":[49],"a":[50,116,175],"tremendous":[51],"amount":[52],"information":[54,75],"for":[55,102],"clustering":[56,156],"purposes.":[57],"However,":[58],"relative":[60],"importance":[61],"this":[63,132,136],"difficult":[67],"to":[68,85,110,119,126,152,162,166,183],"estimate,":[69],"especially":[70],"when":[71],"some":[72],"noisy.":[77],"cases,":[80],"it":[81,93],"can":[82,94,107],"risky":[84],"incorporate":[86],"process,":[91,105,123],"because":[92],"either":[95],"improve":[96],"quality":[98],"representation":[101],"add":[108],"noise":[109],"process.":[112],"Therefore,":[113],"we":[114,138],"need":[115],"principled":[117],"way":[118],"perform":[120],"so":[124],"maximize":[127],"advantages":[129,186],"using":[131,188],"side":[133],"information.":[134],"paper,":[137],"design":[139],"an":[140,154,190],"algorithm":[141],"combines":[143],"classical":[144],"partitioning":[145],"algorithms":[146],"probabilistic":[148],"models":[149],"order":[151,182],"create":[153],"effective":[155],"approach.":[157,191],"We":[158,170],"then":[159],"show":[160],"how":[161],"extend":[163],"approach":[165],"classification":[168],"problem.":[169],"present":[171],"experimental":[172],"results":[173],"on":[174],"number":[176],"real":[178],"data":[179],"sets":[180],"illustrate":[184]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}