{"id":"https://openalex.org/W2010202182","doi":"https://doi.org/10.1145/2381716.2381775","title":"Unsupervised topic detection model and its application in text categorization","display_name":"Unsupervised topic detection model and its application in text categorization","publication_year":2012,"publication_date":"2012-09-03","ids":{"openalex":"https://openalex.org/W2010202182","doi":"https://doi.org/10.1145/2381716.2381775","mag":"2010202182"},"language":"en","primary_location":{"id":"doi:10.1145/2381716.2381775","doi":"https://doi.org/10.1145/2381716.2381775","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2381716.2381775","pdf_url":null,"source":{"id":"https://openalex.org/S4306524033","display_name":"CUBE International Information Technology Conference (CUBE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CUBE International Information Technology Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5039952436","display_name":"Yashodhara V. Haribhakta","orcid":"https://orcid.org/0000-0003-3882-4091","observed_orcids":["https://orcid.org/0000-0003-3882-4091"]},"institutions":[{"id":"https://openalex.org/I4405273661","display_name":"COEP Technological University","ror":"https://ror.org/008128n17","country_code":"IN","type":"education","lineage":["https://openalex.org/I4405273661"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Yashodhara Haribhakta","raw_affiliation_strings":["College of Engineering, Pune Shivajinagar, Pune Maharashtra, India","College of Engineering, Pune Shivajinagar, Pune, Maharashtra, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, Pune Shivajinagar, Pune Maharashtra, India","institution_ids":["https://openalex.org/I4405273661"]},{"raw_affiliation_string":"College of Engineering, Pune Shivajinagar, Pune, Maharashtra, India#TAB#","institution_ids":["https://openalex.org/I4405273661"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061809741","display_name":"Arti Malgaonkar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405273661","display_name":"COEP Technological University","ror":"https://ror.org/008128n17","country_code":"IN","type":"education","lineage":["https://openalex.org/I4405273661"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arti Malgaonkar","raw_affiliation_strings":["College of Engineering, Pune Shivajinagar, Pune Maharashtra, India","College of Engineering, Pune Shivajinagar, Pune, Maharashtra, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, Pune Shivajinagar, Pune Maharashtra, India","institution_ids":["https://openalex.org/I4405273661"]},{"raw_affiliation_string":"College of Engineering, Pune Shivajinagar, Pune, Maharashtra, India#TAB#","institution_ids":["https://openalex.org/I4405273661"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007347603","display_name":"Parag A. Kulkarni","orcid":"https://orcid.org/0000-0001-9350-4889","observed_orcids":["https://orcid.org/0000-0001-9350-4889"]},"institutions":[{"id":"https://openalex.org/I4405273661","display_name":"COEP Technological University","ror":"https://ror.org/008128n17","country_code":"IN","type":"education","lineage":["https://openalex.org/I4405273661"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Parag Kulkarni","raw_affiliation_strings":["College of Engineering, Pune Shivajinagar, Pune Maharashtra, India","College of Engineering, Pune Shivajinagar, Pune, Maharashtra, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Engineering, Pune Shivajinagar, Pune Maharashtra, India","institution_ids":["https://openalex.org/I4405273661"]},{"raw_affiliation_string":"College of Engineering, Pune Shivajinagar, Pune, Maharashtra, India#TAB#","institution_ids":["https://openalex.org/I4405273661"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405273661"],"apc_list":null,"apc_paid":null,"fwci":0.5193,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.52855481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"314","last_page":"319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.6977999806404114,"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":0.6977999806404114,"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":0.27219998836517334,"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":0.026200000196695328,"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/topic-detection","display_name":"topic extraction","score":0.9010000228881836},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.7919999957084656},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.859000027179718},{"id":"https://openalex.org/keywords/keyword-extraction","display_name":"keyword extraction","score":0.9919999837875366},{"id":"https://openalex.org/keywords/word-decomposition","display_name":"word decomposition","score":0.734000027179718},{"id":"https://openalex.org/keywords/term-frequency","display_name":"term frequency","score":0.8320000171661377},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.9210000038146973},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.9670000076293945},{"id":"https://openalex.org/keywords/bag-of-words-comparison","display_name":"bag-of-words comparison","score":0.8669999837875366}],"concepts":[{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.8488208055496216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8305084705352783},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.7403696179389954},{"id":"https://openalex.org/C2780288562","wikidata":"https://www.wikidata.org/wiki/Q25053353","display_name":"Keyword extraction","level":2,"score":0.6883656978607178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6575263738632202},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6309658288955688},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5888941884040833},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5641278028488159},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.5095208287239075},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.5091585516929626},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4912049174308777},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4784574508666992},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4253767728805542},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07871025800704956},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2381716.2381775","doi":"https://doi.org/10.1145/2381716.2381775","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2381716.2381775","pdf_url":null,"source":{"id":"https://openalex.org/S4306524033","display_name":"CUBE International Information Technology Conference (CUBE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the CUBE International Information Technology Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W99763903","https://openalex.org/W1557744248","https://openalex.org/W1933629536","https://openalex.org/W1965129197","https://openalex.org/W1993318811","https://openalex.org/W2031740031","https://openalex.org/W2066733218","https://openalex.org/W2080179128","https://openalex.org/W2089870669","https://openalex.org/W2099283426","https://openalex.org/W2118020653","https://openalex.org/W2121678312","https://openalex.org/W2122098402","https://openalex.org/W2133990480","https://openalex.org/W2165728620","https://openalex.org/W2181733421","https://openalex.org/W4249238488","https://openalex.org/W4254373586","https://openalex.org/W6703074907"],"related_works":["https://openalex.org/W3093509039","https://openalex.org/W7095163355","https://openalex.org/W2975267287","https://openalex.org/W288405627","https://openalex.org/W2122098402","https://openalex.org/W2322557215","https://openalex.org/W2118833229","https://openalex.org/W1558241596","https://openalex.org/W4232857007","https://openalex.org/W2564359861"],"abstract_inverted_index":{"In":[0,58],"most":[1,170,265],"of":[2,12,20,41,55,102,109,142,162,210,255,266,271,279],"the":[3,10,18,35,46,53,56,86,94,97,126,145,169,180,184,196,204,224,227,244,253,256,267,288,295],"research,":[4],"topic":[5,23,30,54,65,80,163,172,189],"detection":[6,24,66,81],"is":[7,26,48,50,73,115,212,258],"defined":[8,51],"as":[9,52,218],"task":[11],"finding":[13,28,83,203],"out":[14],"different":[15],"themes":[16],"from":[17,85,144],"collection":[19],"documents.":[21],"Our":[22],"approach":[25,67,78,278],"about":[27,49],"a":[29,63,74,100],"for":[31,79,120,155,173,202,220,282,298],"every":[32],"document":[33,47,157],"in":[34,99,128,179,264],"corpus.":[36,87],"Any":[37],"word":[38,121,132,147],"or":[39,130],"group":[40],"words":[42,98,127,136,143,230],"which":[43,123],"tells":[44],"what":[45],"document.":[57,175,245],"this":[59],"paper,":[60],"we":[61],"propose":[62],"novel":[64],"using":[68,158,215,249],"an":[69,118],"unsupervised":[70],"model.":[71],"It":[72],"simple":[75],"yet":[76],"effective":[77],"and":[82,183,192,208,222,263],"keywords":[84,89,185,211,217,250],"The":[88,112,165,176,206,232,246],"are":[90,153,190,238],"extracted":[91],"by":[92,214,235],"identifying":[93],"relationship":[95],"between":[96],"set":[101,108],"unstructured":[103],"data":[104],"automatically,":[105],"without":[106],"any":[107],"training":[110],"data.":[111],"keyword":[113,150],"extraction":[114],"based":[116],"on":[117],"hypothesis":[119],"decomposition":[122],"says":[124],"that":[125,137,252,276],"bigram":[129],"trigram":[131],"vectors":[133],"would":[134],"have":[135],"can":[138],"be":[139,241],"potential":[140],"distribution":[141],"unigram":[146],"vector.":[148],"After":[149],"extraction,":[151],"topics":[152,177,233],"determined":[154],"each":[156,174,188],"our":[159,236,277],"proposed":[160,166],"algorithm":[161,167,237],"detection.":[164],"finds":[168],"suitable":[171],"detected":[178,234],"entire":[181],"corpus":[182,257],"related":[186],"with":[187],"stored":[191],"analyzed.":[193],"We":[194],"use":[195],"standard":[197,228],"term":[198],"frequency":[199],"(TF)":[200],"measure":[201],"keywords.":[205],"effectiveness":[207],"accuracy":[209,290],"judged":[213],"these":[216],"features":[219],"classification":[221,289],"comparing":[223],"results":[225,248],"against":[226],"bag-of-":[229],"approach.":[231],"found":[239],"to":[240,243],"relevant":[242],"experimental":[247],"show":[251],"dimensionality":[254],"drastically":[259],"reduced":[260],"while":[261],"maintaining":[262],"cases,":[268],"improving":[269],"F-measure":[270],"categorization.":[272],"Thus,":[273],"it":[274],"shows":[275],"feature":[280],"selection":[281],"text":[283],"categorization":[284],"not":[285],"only":[286],"improves":[287],"but":[291],"also":[292],"reduces":[293],"considerably":[294],"time":[296],"required":[297],"classification.":[299]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2016-06-24T00:00:00"}