{"id":"https://openalex.org/W2946517734","doi":"https://doi.org/10.3233/ida-184045","title":"A practical algorithm for solving the sparseness problem of short text clustering","display_name":"A practical algorithm for solving the sparseness problem of short text clustering","publication_year":2019,"publication_date":"2019-04-29","ids":{"openalex":"https://openalex.org/W2946517734","doi":"https://doi.org/10.3233/ida-184045","mag":"2946517734"},"language":"en","primary_location":{"id":"doi:10.3233/ida-184045","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ida-184045","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"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":"Intelligent Data Analysis","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/A5062724090","display_name":"Jipeng Qiang","orcid":"https://orcid.org/0000-0001-5721-0293"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jipeng Qiang","raw_affiliation_strings":["Department of Computer Science, Yangzhou University, Yangzhou, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yangzhou University, Yangzhou, Jiangsu, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101793983","display_name":"Yun Li","orcid":"https://orcid.org/0000-0002-7628-0358"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yun Li","raw_affiliation_strings":["Department of Computer Science, Yangzhou University, Yangzhou, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yangzhou University, Yangzhou, Jiangsu, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055757510","display_name":"Yunhao Yuan","orcid":"https://orcid.org/0000-0003-3712-443X"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunhao Yuan","raw_affiliation_strings":["Department of Computer Science, Yangzhou University, Yangzhou, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yangzhou University, Yangzhou, Jiangsu, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081284604","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0001-8503-4063"},"institutions":[{"id":"https://openalex.org/I78978612","display_name":"Yangzhou University","ror":"https://ror.org/03tqb8s11","country_code":"CN","type":"education","lineage":["https://openalex.org/I78978612"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["Department of Computer Science, Yangzhou University, Yangzhou, Jiangsu, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Yangzhou University, Yangzhou, Jiangsu, China","institution_ids":["https://openalex.org/I78978612"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080738591","display_name":"Xindong Wu","orcid":"https://orcid.org/0000-0003-2396-1704"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xindong Wu","raw_affiliation_strings":["School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA"],"affiliations":[{"raw_affiliation_string":"School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA","institution_ids":["https://openalex.org/I79516672"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101793983"],"corresponding_institution_ids":["https://openalex.org/I78978612"],"apc_list":null,"apc_paid":null,"fwci":0.5601,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74257291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"23","issue":"3","first_page":"701","last_page":"716"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9961000084877014,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9894999861717224,"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/computer-science","display_name":"Computer science","score":0.7383124828338623},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.7080089449882507},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6273088455200195},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5935418605804443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5918386578559875},{"id":"https://openalex.org/keywords/multinomial-distribution","display_name":"Multinomial distribution","score":0.46452558040618896},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4201469421386719},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.41696426272392273},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.41101667284965515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17335066199302673},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.16629913449287415},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08026066422462463}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7383124828338623},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.7080089449882507},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6273088455200195},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5935418605804443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5918386578559875},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.46452558040618896},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4201469421386719},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.41696426272392273},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.41101667284965515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17335066199302673},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.16629913449287415},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08026066422462463},{"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:10.3233/ida-184045","is_oa":false,"landing_page_url":"https://doi.org/10.3233/ida-184045","pdf_url":null,"source":{"id":"https://openalex.org/S2498839158","display_name":"Intelligent Data Analysis","issn_l":"1088-467X","issn":["1088-467X","1571-4128"],"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":"Intelligent Data Analysis","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1880262756","https://openalex.org/W1989753615","https://openalex.org/W1993691975","https://openalex.org/W2001082470","https://openalex.org/W2061922307","https://openalex.org/W2088314245","https://openalex.org/W2097089247","https://openalex.org/W2097417931","https://openalex.org/W2135029798","https://openalex.org/W2138615112","https://openalex.org/W2142827986","https://openalex.org/W2155498061","https://openalex.org/W2162833336","https://openalex.org/W2165232124","https://openalex.org/W2222893162","https://openalex.org/W2250539671","https://openalex.org/W2250545651","https://openalex.org/W2251103205","https://openalex.org/W2279005194","https://openalex.org/W2380042537","https://openalex.org/W2382102351","https://openalex.org/W2511329098","https://openalex.org/W2516537890","https://openalex.org/W2550859505","https://openalex.org/W2576754561","https://openalex.org/W2739266293","https://openalex.org/W2743763476","https://openalex.org/W2745475103","https://openalex.org/W2750733752","https://openalex.org/W2949547296","https://openalex.org/W2963726741","https://openalex.org/W4235169531","https://openalex.org/W4294170691","https://openalex.org/W4299345493","https://openalex.org/W6600137863","https://openalex.org/W6629028937","https://openalex.org/W6639619044","https://openalex.org/W6666227387","https://openalex.org/W6674864096","https://openalex.org/W6680012447","https://openalex.org/W6680970901","https://openalex.org/W6682691769","https://openalex.org/W6689050917","https://openalex.org/W6691393457","https://openalex.org/W6709779263","https://openalex.org/W6710049685","https://openalex.org/W6741496569"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W3005513013","https://openalex.org/W2207653751","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W4389543811"],"abstract_inverted_index":{"Dirichlet":[0],"Multinomial":[1],"Mixture":[2],"(DMM)":[3],"models":[4,23,45],"have":[5,35],"been":[6],"successful":[7],"in":[8,41,91,103,126],"clustering":[9],"short":[10,28,42,85,104],"texts.":[11,105],"However,":[12],"the":[13,27,50,54,99,107,135,143],"word":[14],"co-occurrence":[15],"information":[16],"that":[17,94],"can":[18,46,95],"be":[19],"captured":[20],"by":[21,65,117,122],"these":[22,44],"is":[24,113],"limited":[25],"to":[26,97],"text":[29,86,93,112],"corpus":[30],"itself.":[31],"If":[32],"two":[33,55],"words":[34,90,125],"strong":[36],"relatedness":[37,52],"but":[38,120],"rarely":[39],"co-occurring":[40],"texts,":[43],"not":[47,114],"fully":[48],"capture":[49],"semantic":[51],"between":[53],"words.":[56],"In":[57],"this":[58,127],"paper,":[59],"we":[60],"propose":[61],"a":[62,75],"novel":[63],"model":[64,82,141],"incorporating":[66],"word-word":[67,79],"correlation":[68],"into":[69],"DMM,":[70],"called":[71],"WDMM.":[72],"By":[73],"constructing":[74],"sparse":[76],"graph":[77],"using":[78,87],"relationship,":[80],"our":[81,139],"expands":[83],"each":[84,92,111],"their":[88,123],"neighboring":[89],"help":[96],"solve":[98],"problem":[100],"of":[101,110,138],"sparseness":[102],"Therefore,":[106],"cluster":[108],"label":[109],"only":[115],"influenced":[116],"its":[118],"words,":[119],"decided":[121],"similar":[124],"corpus.":[128],"Experimental":[129],"results":[130],"on":[131],"real-world":[132],"datasets":[133],"demonstrated":[134],"substantial":[136],"superiority":[137],"WDMM":[140],"over":[142],"state-of-the-art":[144],"methods.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}