{"id":"https://openalex.org/W4396778939","doi":"https://doi.org/10.1186/s40537-024-00930-9","title":"Hybrid topic modeling method based on dirichlet multinomial mixture and fuzzy match algorithm for short text clustering","display_name":"Hybrid topic modeling method based on dirichlet multinomial mixture and fuzzy match algorithm for short text clustering","publication_year":2024,"publication_date":"2024-05-09","ids":{"openalex":"https://openalex.org/W4396778939","doi":"https://doi.org/10.1186/s40537-024-00930-9"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-024-00930-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00930-9","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00930-9","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00930-9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086205276","display_name":"Mutasem K. Alsmadi","orcid":"https://orcid.org/0000-0001-6892-8399"},"institutions":[{"id":"https://openalex.org/I76571253","display_name":"Imam Abdulrahman Bin Faisal University","ror":"https://ror.org/038cy8j79","country_code":"SA","type":"education","lineage":["https://openalex.org/I76571253"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Mutasem K. Alsmadi","raw_affiliation_strings":["Department of MIS, College of Applied Studies and Community Service, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of MIS, College of Applied Studies and Community Service, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia","institution_ids":["https://openalex.org/I76571253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026875260","display_name":"Malek Alzaqebah","orcid":"https://orcid.org/0000-0002-3846-0673"},"institutions":[{"id":"https://openalex.org/I76571253","display_name":"Imam Abdulrahman Bin Faisal University","ror":"https://ror.org/038cy8j79","country_code":"SA","type":"education","lineage":["https://openalex.org/I76571253"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Malek Alzaqebah","raw_affiliation_strings":["Basic and Applied Scientific Research Center, Imam Abdulrahman Bin Faisal University, P. O. Box 1982, Dammam, Saudi Arabia","Department of Mathematics, College of Science, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basic and Applied Scientific Research Center, Imam Abdulrahman Bin Faisal University, P. O. Box 1982, Dammam, Saudi Arabia","institution_ids":["https://openalex.org/I76571253"]},{"raw_affiliation_string":"Department of Mathematics, College of Science, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia","institution_ids":["https://openalex.org/I76571253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014707709","display_name":"Sana Jawarneh","orcid":"https://orcid.org/0000-0002-9863-3775"},"institutions":[{"id":"https://openalex.org/I76571253","display_name":"Imam Abdulrahman Bin Faisal University","ror":"https://ror.org/038cy8j79","country_code":"SA","type":"education","lineage":["https://openalex.org/I76571253"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Sana Jawarneh","raw_affiliation_strings":["Computer Science Department, Community College Dammam, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Community College Dammam, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia","institution_ids":["https://openalex.org/I76571253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082179107","display_name":"Ibrahim Almarashdeh","orcid":"https://orcid.org/0000-0001-6477-4679"},"institutions":[{"id":"https://openalex.org/I76571253","display_name":"Imam Abdulrahman Bin Faisal University","ror":"https://ror.org/038cy8j79","country_code":"SA","type":"education","lineage":["https://openalex.org/I76571253"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Ibrahim ALmarashdeh","raw_affiliation_strings":["Department of MIS, College of Applied Studies and Community Service, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of MIS, College of Applied Studies and Community Service, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia","institution_ids":["https://openalex.org/I76571253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081678536","display_name":"Mohammed Azmi Al\u2010Betar","orcid":"https://orcid.org/0000-0003-1980-1791"},"institutions":[{"id":"https://openalex.org/I182000528","display_name":"Ajman University","ror":"https://ror.org/01j1rma10","country_code":"AE","type":"education","lineage":["https://openalex.org/I182000528"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mohammed Azmi Al-Betar","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), College of Engineering and Information Technology, Ajman University, Ajman, United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), College of Engineering and Information Technology, Ajman University, Ajman, United Arab Emirates","institution_ids":["https://openalex.org/I182000528"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090628443","display_name":"Maram Alwohaibi","orcid":"https://orcid.org/0000-0002-1873-7911"},"institutions":[{"id":"https://openalex.org/I76571253","display_name":"Imam Abdulrahman Bin Faisal University","ror":"https://ror.org/038cy8j79","country_code":"SA","type":"education","lineage":["https://openalex.org/I76571253"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Maram Alwohaibi","raw_affiliation_strings":["Basic and Applied Scientific Research Center, Imam Abdulrahman Bin Faisal University, P. O. Box 1982, Dammam, Saudi Arabia","Department of Mathematics, College of Science, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basic and Applied Scientific Research Center, Imam Abdulrahman Bin Faisal University, P. O. Box 1982, Dammam, Saudi Arabia","institution_ids":["https://openalex.org/I76571253"]},{"raw_affiliation_string":"Department of Mathematics, College of Science, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia","institution_ids":["https://openalex.org/I76571253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026203277","display_name":"Noha A. Al-Mulla","orcid":null},"institutions":[{"id":"https://openalex.org/I76571253","display_name":"Imam Abdulrahman Bin Faisal University","ror":"https://ror.org/038cy8j79","country_code":"SA","type":"education","lineage":["https://openalex.org/I76571253"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Noha A. Al-Mulla","raw_affiliation_strings":["Basic and Applied Scientific Research Center, Imam Abdulrahman Bin Faisal University, P. O. Box 1982, Dammam, Saudi Arabia","Department of Mathematics, College of Science, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basic and Applied Scientific Research Center, Imam Abdulrahman Bin Faisal University, P. O. Box 1982, Dammam, Saudi Arabia","institution_ids":["https://openalex.org/I76571253"]},{"raw_affiliation_string":"Department of Mathematics, College of Science, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia","institution_ids":["https://openalex.org/I76571253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111192536","display_name":"Eman AE Ahmed","orcid":null},"institutions":[{"id":"https://openalex.org/I76571253","display_name":"Imam Abdulrahman Bin Faisal University","ror":"https://ror.org/038cy8j79","country_code":"SA","type":"education","lineage":["https://openalex.org/I76571253"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Eman AE Ahmed","raw_affiliation_strings":["Basic and Applied Scientific Research Center, Imam Abdulrahman Bin Faisal University, P. O. Box 1982, Dammam, Saudi Arabia","Department of Mathematics, College of Science, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Basic and Applied Scientific Research Center, Imam Abdulrahman Bin Faisal University, P. O. Box 1982, Dammam, Saudi Arabia","institution_ids":["https://openalex.org/I76571253"]},{"raw_affiliation_string":"Department of Mathematics, College of Science, Imam Abdulrahman Bin Faisal University, Dammam, Saudi Arabia","institution_ids":["https://openalex.org/I76571253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007234619","display_name":"Ahmad Al Smadi","orcid":"https://orcid.org/0000-0003-3487-8041"},"institutions":[{"id":"https://openalex.org/I153687341","display_name":"Zarqa University","ror":"https://ror.org/01wf1es90","country_code":"JO","type":"education","lineage":["https://openalex.org/I153687341"]}],"countries":["JO"],"is_corresponding":false,"raw_author_name":"Ahmad AL Smadi","raw_affiliation_strings":["Department of Data Science and Artificial Intelligence, Zarqa University, Zarqa 13100, Jordan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science and Artificial Intelligence, Zarqa University, Zarqa 13100, Jordan","institution_ids":["https://openalex.org/I153687341"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5086205276"],"corresponding_institution_ids":["https://openalex.org/I76571253"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":2.8322,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91484712,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"11","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T11550","display_name":"Text and Document Classification Technologies","score":0.9958000183105469,"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":0.9872999787330627,"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/levenshtein-distance","display_name":"Levenshtein distance","score":0.8651880025863647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8147979974746704},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.7935787439346313},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6899039149284363},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.591860294342041},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4975109398365021},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46768954396247864},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.4505947530269623},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4267715811729431},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.4176831543445587},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41141682863235474},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4094601273536682},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32346463203430176}],"concepts":[{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.8651880025863647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8147979974746704},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7935787439346313},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6899039149284363},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.591860294342041},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4975109398365021},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46768954396247864},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.4505947530269623},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4267715811729431},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.4176831543445587},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41141682863235474},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4094601273536682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32346463203430176},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-024-00930-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00930-9","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00930-9","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:3a77b2ad8c6b4d1198856d4083223042","is_oa":true,"landing_page_url":"https://doaj.org/article/3a77b2ad8c6b4d1198856d4083223042","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 11, Iss 1, Pp 1-21 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-024-00930-9","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-024-00930-9","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-024-00930-9","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G7372779242","display_name":null,"funder_award_id":"BASRC-083-2020","funder_id":"https://openalex.org/F4320328818","funder_display_name":"Imam Abdulrahman Bin Faisal University"}],"funders":[{"id":"https://openalex.org/F4320328818","display_name":"Imam Abdulrahman Bin Faisal University","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4396778939.pdf"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W40976687","https://openalex.org/W84258197","https://openalex.org/W1966863499","https://openalex.org/W1989753615","https://openalex.org/W2001082470","https://openalex.org/W2048195127","https://openalex.org/W2052261215","https://openalex.org/W2054997212","https://openalex.org/W2061922307","https://openalex.org/W2087743880","https://openalex.org/W2097089247","https://openalex.org/W2097417931","https://openalex.org/W2136317725","https://openalex.org/W2142827986","https://openalex.org/W2165232124","https://openalex.org/W2171343266","https://openalex.org/W2252067490","https://openalex.org/W2303303248","https://openalex.org/W2342605519","https://openalex.org/W2442340835","https://openalex.org/W2511329098","https://openalex.org/W2625475744","https://openalex.org/W2737717567","https://openalex.org/W2750733752","https://openalex.org/W2754014686","https://openalex.org/W2759575792","https://openalex.org/W2768113420","https://openalex.org/W2841402245","https://openalex.org/W2887928931","https://openalex.org/W2911593082","https://openalex.org/W2963726741","https://openalex.org/W2978342152","https://openalex.org/W2981204173","https://openalex.org/W2991519662","https://openalex.org/W3027457715","https://openalex.org/W3034719632","https://openalex.org/W3080853733","https://openalex.org/W3095278059","https://openalex.org/W3125213666","https://openalex.org/W3129831852","https://openalex.org/W3154302539","https://openalex.org/W3183747776","https://openalex.org/W3197134633","https://openalex.org/W3204635633","https://openalex.org/W3209650954","https://openalex.org/W3213117297","https://openalex.org/W4210678334","https://openalex.org/W4231510805","https://openalex.org/W4241252752","https://openalex.org/W4255519208","https://openalex.org/W4284960486","https://openalex.org/W4300672471","https://openalex.org/W4307321238","https://openalex.org/W4376609806","https://openalex.org/W4384461115"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W4293863151","https://openalex.org/W3159709618","https://openalex.org/W4309228610","https://openalex.org/W4294597112"],"abstract_inverted_index":{"Abstract":[0],"Topic":[1,94],"modeling":[2,44,130,205],"methods":[3,45,56],"proved":[4],"to":[5,28,51,75,78,116,167,177,202,229,250],"be":[6,52],"effective":[7],"for":[8,23],"inferring":[9],"latent":[10],"topics":[11,50,69,147],"from":[12],"short":[13,17,244],"texts.":[14],"Dealing":[15],"with":[16,207],"texts":[18,245],"is":[19,73,102],"challenging":[20],"yet":[21],"helpful":[22],"many":[24,82],"real-world":[25],"applications,":[26],"due":[27,77],"the":[29,33,36,42,47,64,86,93,112,137,144,155,169,172,189,192,235,242],"sparse":[30],"terms":[31],"in":[32,85,104,121,128,171,200,210,215],"text":[34],"and":[35,81,111,152,212,234],"high":[37],"dimensionality":[38],"representation.":[39],"Most":[40],"of":[41,49,68,135,140,191,241],"topic":[43,79,122,129,204],"require":[46],"number":[48,67,139],"defined":[53],"earlier.":[54],"Similarly,":[55],"based":[57,97],"on":[58,98],"Dirichlet":[59],"Multinomial":[60],"Mixture":[61],"(DMM)":[62],"involve":[63],"maximum":[65],"possible":[66],"before":[70],"execution":[71],"which":[72],"hard":[74],"determine":[76],"uncertainty,":[80],"noises":[83],"exist":[84],"dataset.":[87],"Hence,":[88],"a":[89,230],"new":[90],"approach":[91,194],"called":[92],"Clustering":[95],"algorithm":[96,115],"Levenshtein":[99,161],"Distance":[100],"(TCLD)":[101],"introduced":[103],"this":[105],"paper,":[106],"TCLD":[107,142],"combines":[108],"DMM":[109,150],"models":[110,151],"Fuzzy":[113],"matching":[114],"address":[117],"two":[118],"key":[119],"challenges":[120],"modeling:":[123],"(a)":[124],"The":[125,133,186,223],"outlier":[126],"problem":[127,134],"methods.":[131],"(b)":[132],"determining":[136],"optimal":[138],"topics.":[141],"uses":[143],"initial":[145],"clustered":[146],"generated":[148],"by":[149],"then":[153],"evaluates":[154],"semantic":[156],"relationships":[157],"between":[158],"documents":[159],"using":[160],"Distance.":[162],"Subsequently,":[163],"it":[164,176,182],"determines":[165],"whether":[166],"keep":[168],"document":[170],"same":[173],"cluster,":[174,179],"relocate":[175],"another":[178],"or":[180],"mark":[181],"as":[183],"an":[184],"outlier.":[185],"results":[187,236],"demonstrate":[188],"efficiency":[190],"proposed":[193,224],"across":[195,220],"six":[196],"English":[197],"benchmark":[198],"datasets,":[199],"comparison":[201],"seven":[203],"approaches,":[206],"83%":[208],"improvement":[209],"purity":[211],"67%":[213],"enhancement":[214],"Normalized":[216],"Mutual":[217],"Information":[218],"(NMI)":[219],"all":[221],"datasets.":[222],"method":[225],"was":[226],"also":[227],"applied":[228],"collected":[231],"Arabic":[232,243],"tweet":[233],"showed":[237],"that":[238],"only":[239],"12%":[240],"were":[246],"incorrectly":[247],"clustered,":[248],"according":[249],"human":[251],"inspection.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
