{"id":"https://openalex.org/W2938684013","doi":"https://doi.org/10.3233/jifs-179015","title":"Scalable text semantic clustering around topics","display_name":"Scalable text semantic clustering around topics","publication_year":2019,"publication_date":"2019-04-15","ids":{"openalex":"https://openalex.org/W2938684013","doi":"https://doi.org/10.3233/jifs-179015","mag":"2938684013"},"language":"en","primary_location":{"id":"doi:10.3233/jifs-179015","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-179015","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Fuzzy Systems","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/A5038666616","display_name":"Ram\u00f3n Brena","orcid":"https://orcid.org/0000-0002-0995-2273"},"institutions":[{"id":"https://openalex.org/I98461037","display_name":"Tecnol\u00f3gico de Monterrey","ror":"https://ror.org/03ayjn504","country_code":"MX","type":"education","lineage":["https://openalex.org/I98461037"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Ramon Brena","raw_affiliation_strings":["Tecnologico de Monterrey, Av. E. Garza Sada 2501, Monterrey, Mexico"],"affiliations":[{"raw_affiliation_string":"Tecnologico de Monterrey, Av. E. Garza Sada 2501, Monterrey, Mexico","institution_ids":["https://openalex.org/I98461037"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110127299","display_name":"Eduardo Ram\u00edrez","orcid":null},"institutions":[{"id":"https://openalex.org/I98461037","display_name":"Tecnol\u00f3gico de Monterrey","ror":"https://ror.org/03ayjn504","country_code":"MX","type":"education","lineage":["https://openalex.org/I98461037"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Eduardo Ramirez","raw_affiliation_strings":["Tecnologico de Monterrey, Av. E. Garza Sada 2501, Monterrey, Mexico"],"affiliations":[{"raw_affiliation_string":"Tecnologico de Monterrey, Av. E. Garza Sada 2501, Monterrey, Mexico","institution_ids":["https://openalex.org/I98461037"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5038666616"],"corresponding_institution_ids":["https://openalex.org/I98461037"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03097214,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"5","first_page":"4645","last_page":"4657"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/T10028","display_name":"Topic Modeling","score":0.9976999759674072,"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/T11719","display_name":"Data Quality and Management","score":0.9908999800682068,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.875603199005127},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.8510804176330566},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7503488063812256},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6765259504318237},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5549156665802002},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5137423276901245},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4702181816101074},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4461980164051056},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.4440159201622009},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43080997467041016},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4245147407054901},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3954116106033325},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36039406061172485},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35880643129348755},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34973227977752686},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13296544551849365},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.1185251772403717}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.875603199005127},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8510804176330566},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7503488063812256},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6765259504318237},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5549156665802002},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5137423276901245},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4702181816101074},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4461980164051056},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.4440159201622009},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43080997467041016},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4245147407054901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3954116106033325},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36039406061172485},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35880643129348755},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34973227977752686},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13296544551849365},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.1185251772403717},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jifs-179015","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jifs-179015","pdf_url":null,"source":{"id":"https://openalex.org/S179157397","display_name":"Journal of Intelligent & Fuzzy Systems","issn_l":"1064-1246","issn":["1064-1246","1875-8967"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Intelligent &amp; Fuzzy Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1499469283","https://openalex.org/W1524701945","https://openalex.org/W1686946872","https://openalex.org/W1732828232","https://openalex.org/W1880262756","https://openalex.org/W1972622791","https://openalex.org/W1982433219","https://openalex.org/W1984251878","https://openalex.org/W1984565341","https://openalex.org/W2010425028","https://openalex.org/W2030644393","https://openalex.org/W2040427737","https://openalex.org/W2042980227","https://openalex.org/W2060314721","https://openalex.org/W2073965851","https://openalex.org/W2079168273","https://openalex.org/W2079306104","https://openalex.org/W2099111195","https://openalex.org/W2099111758","https://openalex.org/W2102381086","https://openalex.org/W2109803107","https://openalex.org/W2113843799","https://openalex.org/W2117309679","https://openalex.org/W2127164716","https://openalex.org/W2127314673","https://openalex.org/W2128925311","https://openalex.org/W2142120379","https://openalex.org/W2146341620","https://openalex.org/W2147152072","https://openalex.org/W2153029569","https://openalex.org/W2174706414","https://openalex.org/W2250753706","https://openalex.org/W2313093213","https://openalex.org/W2330846461","https://openalex.org/W2434205482","https://openalex.org/W2604272474","https://openalex.org/W3099640513","https://openalex.org/W4233135949","https://openalex.org/W4237623536","https://openalex.org/W6637108112","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4389760904","https://openalex.org/W4306886878","https://openalex.org/W2155531513"],"abstract_inverted_index":{"Detection":[0],"of":[1,38,75,80,90,108,112,118,122,167,178],"topics":[2,32,76],"in":[3,55,137,142],"Natural":[4],"Language":[5],"text":[6,15,20],"collections":[7],"is":[8,85,100],"an":[9,65,101],"important":[10],"step":[11],"towards":[12],"flexible":[13],"automated":[14],"handling,":[16],"for":[17],"tasks":[18],"like":[19],"translation,":[21],"summarization,":[22],"etc.":[23],"In":[24,60],"the":[25,106,119,123,162,179],"current":[26],"dominant":[27],"paradigm":[28,69],"to":[29,53,87],"topic":[30,67],"modeling,":[31],"are":[33,43],"represented":[34],"as":[35,77],"probability":[36],"distributions":[37],"terms.":[39],"Although":[40],"such":[41],"models":[42,127,166],"theoretically":[44],"sound,":[45],"their":[46],"high":[47],"computational":[48],"complexity":[49,151],"makes":[50],"them":[51],"difficult":[52],"use":[54],"very":[56],"large":[57],"scale":[58],"collections.":[59],"this":[61],"work":[62],"we":[63,149],"propose":[64],"alternative":[66],"modeling":[68],"based":[70],"on":[71],"a":[72,109,145],"simpler":[73],"representation":[74],"overlapping":[78],"clusters":[79],"semantically":[81],"similar":[82],"documents,":[83],"that":[84,104,114,153,161],"able":[86],"take":[88],"advantage":[89],"highly-scalable":[91],"clustering":[92],"algorithms.":[93],"Our":[94,158],"Query-based":[95],"Topic":[96],"Modeling":[97],"framework":[98],"(QTM)":[99],"information-theoretic":[102],"method":[103],"assumes":[105],"existence":[107],"\u201cgolden\u201d":[110],"set":[111],"queries":[113],"can":[115,164],"capture":[116],"most":[117],"semantic":[120],"information":[121],"collection":[124],"and":[125,139],"produce":[126,165],"with":[128,135],"maximum":[129],"\u201csemantic":[130],"coherence\u201d.":[131],"QTM":[132,163],"was":[133,140],"designed":[134],"scalability":[136,156],"mind":[138],"executed":[141],"parallel":[143],"using":[144],"Map-Reduce":[146],"implementation;":[147],"further,":[148],"show":[150,160],"measures":[152],"support":[154],"our":[155],"claims.":[157],"experiments":[159],"comparable":[168],"or":[169],"even":[170],"superior":[171],"quality":[172],"than":[173],"those":[174],"produced":[175],"by":[176],"state":[177],"art":[180],"probabilistic":[181],"methods.":[182]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
