{"id":"https://openalex.org/W3016384020","doi":"https://doi.org/10.1177/0165551520911590","title":"An ensemble clustering approach for topic discovery using implicit text segmentation","display_name":"An ensemble clustering approach for topic discovery using implicit text segmentation","publication_year":2020,"publication_date":"2020-04-14","ids":{"openalex":"https://openalex.org/W3016384020","doi":"https://doi.org/10.1177/0165551520911590","mag":"3016384020"},"language":"en","primary_location":{"id":"doi:10.1177/0165551520911590","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551520911590","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","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/A5074895294","display_name":"Muhammad Qasim Memon","orcid":"https://orcid.org/0000-0001-6380-9315"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muhammad Qasim Memon","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, China"],"raw_orcid":"https://orcid.org/0000-0001-6380-9315","affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101645258","display_name":"Yu Lu","orcid":"https://orcid.org/0000-0003-2378-4971"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yu Lu","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069621833","display_name":"Penghe Chen","orcid":"https://orcid.org/0000-0003-1894-3552"},"institutions":[{"id":"https://openalex.org/I25254941","display_name":"Beijing Normal University","ror":"https://ror.org/022k4wk35","country_code":"CN","type":"education","lineage":["https://openalex.org/I25254941"]},{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Penghe Chen","raw_affiliation_strings":["Advanced Innovation Center for Future Education, Faculty of Education, Beijing Normal University, China","Faculty of Information Technology, Beijing University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Advanced Innovation Center for Future Education, Faculty of Education, Beijing Normal University, China","institution_ids":["https://openalex.org/I25254941"]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003112843","display_name":"Aasma Memon","orcid":"https://orcid.org/0000-0002-0633-391X"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aasma Memon","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, China","School of Economics and Management, Beijing University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"School of Economics and Management, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051139581","display_name":"Muhammad Salman Pathan","orcid":"https://orcid.org/0000-0002-0210-3121"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Muhammad Salman Pathan","raw_affiliation_strings":["College of Computer Science, Beijing University of Technology, China","Faculty of Information Technology, Beijing University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074272533","display_name":"Zulfiqar Ali Zardari","orcid":"https://orcid.org/0000-0002-1970-3078"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zulfiqar Ali Zardari","raw_affiliation_strings":["Faculty of Information Technology, Beijing University of Technology, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, Beijing University of Technology, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101645258"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.5417,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.72804918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"47","issue":"4","first_page":"431","last_page":"457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9979000091552734,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9979000091552734,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9939000010490417,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.989300012588501,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8718019127845764},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.7688952088356018},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7402170896530151},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6186254024505615},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5233528017997742},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.46790963411331177},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.4651682376861572},{"id":"https://openalex.org/keywords/text-segmentation","display_name":"Text segmentation","score":0.45993614196777344},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.45817869901657104},{"id":"https://openalex.org/keywords/consensus-clustering","display_name":"Consensus clustering","score":0.4393256604671478},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.4253776967525482},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4047762453556061},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.39672261476516724},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3846004009246826},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.1842348575592041}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8718019127845764},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.7688952088356018},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7402170896530151},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6186254024505615},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5233528017997742},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.46790963411331177},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.4651682376861572},{"id":"https://openalex.org/C98501671","wikidata":"https://www.wikidata.org/wiki/Q1948408","display_name":"Text segmentation","level":3,"score":0.45993614196777344},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.45817869901657104},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.4393256604671478},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.4253776967525482},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4047762453556061},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.39672261476516724},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3846004009246826},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.1842348575592041},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0165551520911590","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551520911590","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G8115670746","display_name":null,"funder_award_id":"No. 17YJCZH116","funder_id":"https://openalex.org/F4320335982","funder_display_name":"Humanities and Social Science Fund of Ministry of Education of China"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null},{"id":"https://openalex.org/F4320335982","display_name":"Humanities and Social Science Fund of Ministry of Education of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W977114758","https://openalex.org/W1557074680","https://openalex.org/W1593552591","https://openalex.org/W1828401780","https://openalex.org/W1979469248","https://openalex.org/W2015191210","https://openalex.org/W2022166150","https://openalex.org/W2066651513","https://openalex.org/W2075117036","https://openalex.org/W2080133951","https://openalex.org/W2083593596","https://openalex.org/W2088467494","https://openalex.org/W2089421272","https://openalex.org/W2106706098","https://openalex.org/W2142522063","https://openalex.org/W2150102617","https://openalex.org/W2159083595","https://openalex.org/W2162384303","https://openalex.org/W2224746910","https://openalex.org/W2398936787","https://openalex.org/W2462044331","https://openalex.org/W2469451260","https://openalex.org/W2508074026","https://openalex.org/W2529085631","https://openalex.org/W2728918951","https://openalex.org/W2757021967","https://openalex.org/W2790446200","https://openalex.org/W2802888953","https://openalex.org/W2810542905","https://openalex.org/W2884056776","https://openalex.org/W2903296288","https://openalex.org/W2912814679","https://openalex.org/W2964252866","https://openalex.org/W2974231781","https://openalex.org/W3099154743","https://openalex.org/W4206070039","https://openalex.org/W4241589526","https://openalex.org/W4245826852","https://openalex.org/W4287890950"],"related_works":["https://openalex.org/W2954628966","https://openalex.org/W2130194910","https://openalex.org/W2042494732","https://openalex.org/W58095113","https://openalex.org/W2891223594","https://openalex.org/W2387287989","https://openalex.org/W2019737068","https://openalex.org/W1997571094","https://openalex.org/W2591691005","https://openalex.org/W2007855409"],"abstract_inverted_index":{"Text":[0],"segmentation":[1],"(TS)":[2],"is":[3,83,103,121,141,151,154,206,292],"the":[4,54,91,130,175,196,216,231,258,278],"process":[5],"of":[6,93,111,132,168,178,213,218,233,274],"dividing":[7],"multi-topic":[8,31,69],"text":[9,18,32,70,96,234,298],"collections":[10],"into":[11,114],"cohesive":[12],"segments":[13,115],"using":[14,171],"topic":[15,302],"boundaries.":[16],"Similarly,":[17],"clustering":[19,51,80,87,133,169,199,235],"has":[20],"been":[21],"renowned":[22],"as":[23,34,295],"a":[24,77,84,100,104,109,112,138,163,237],"major":[25],"concern":[26],"when":[27,134,215],"it":[28,135,202],"comes":[29,136],"to":[30,67,137,144,161,186,229],"collections,":[33],"they":[35,190],"are":[36,44,267],"distinguished":[37],"by":[38],"sub-topic":[39],"structure":[40,150],"and":[41,62,95,147,166,182,201,254,260,301],"their":[42],"contents":[43],"not":[45,64],"associated":[46,122],"with":[47,123,129,270],"each":[48,119],"other.":[49],"Existing":[50],"approaches":[52],"follow":[53],"TS":[55,94],"method":[56],"which":[57,89,107],"relies":[58],"on":[59,198],"word":[60],"frequencies":[61],"may":[63],"be":[65,284],"suitable":[66],"cluster":[68],"collections.":[71],"In":[72],"this":[73],"work,":[74],"we":[75],"propose":[76],"new":[78],"ensemble":[79],"approach":[81],"(ECA)":[82],"novel":[85],"topic-modelling-based":[86],"approach,":[88,262],"induces":[90],"combination":[92],"clustering.":[97],"We":[98,127],"improvised":[99],"LDA-onto":[101],"(LDA-ontology)":[102],"TS-based":[105],"model,":[106],"presents":[108],"deterioration":[110],"document":[113,139,296],"(i.e.":[116],"sub-documents),":[117],"wherein":[118],"sub-document":[120],"exactly":[124],"one":[125],"sub-topic.":[126],"deal":[128],"problem":[131,232],"that":[140,189,204,264],"intrinsically":[142],"related":[143],"various":[145],"topics":[146,219],"its":[148],"topical":[149],"missing.":[152],"ECA":[153,173,250],"tested":[155],"through":[156],"well-known":[157],"datasets":[158],"in":[159,180,227,236,286],"order":[160,228],"provide":[162],"comprehensive":[164],"presentation":[165],"validation":[167],"algorithms":[170],"LDA-onto.":[172],"exhibits":[174],"semantic":[176],"relations":[177],"keywords":[179],"sub-documents":[181],"resultant":[183],"clusters":[184],"belong":[185],"original":[187],"documents":[188],"contain.":[191],"Moreover,":[192],"present":[193],"research":[194],"sheds":[195],"light":[197],"performances":[200,210],"indicates":[203],"there":[205],"no":[207],"difference":[208],"over":[209,245,275],"(in":[211],"terms":[212],"F-measure)":[214],"number":[217],"changes.":[220],"Our":[221],"findings":[222],"give":[223],"above":[224],"par":[225],"results":[226,266],"analyse":[230],"broader":[238],"spectrum":[239],"without":[240],"applying":[241],"dimension":[242],"reduction":[243],"techniques":[244],"high":[246],"sparse":[247],"data.":[248],"Specifically,":[249],"provides":[251],"an":[252,271],"efficient":[253],"significant":[255,269],"framework":[256,282],"than":[257],"traditional":[259],"segment-based":[261],"such":[263,294],"achieved":[265],"statistically":[268],"average":[272],"improvement":[273],"10.2%.":[276],"For":[277],"most":[279],"part,":[280],"proposed":[281],"can":[283],"evaluated":[285],"applications":[287],"where":[288],"meaningful":[289],"data":[290],"retrieval":[291],"useful,":[293],"summarization,":[297],"retrieval,":[299],"novelty":[300],"detection.":[303]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-18T08:10:14.011955","created_date":"2025-10-10T00:00:00"}