{"id":"https://openalex.org/W4410481024","doi":"https://doi.org/10.3390/a18050289","title":"Analysis of Short Texts Using Intelligent Clustering Methods","display_name":"Analysis of Short Texts Using Intelligent Clustering Methods","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4410481024","doi":"https://doi.org/10.3390/a18050289"},"language":"en","primary_location":{"id":"doi:10.3390/a18050289","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18050289","pdf_url":"https://www.mdpi.com/1999-4893/18/5/289/pdf?version=1747635461","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/18/5/289/pdf?version=1747635461","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033322678","display_name":"Jamalbek Tussupov","orcid":"https://orcid.org/0000-0002-9179-0428"},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Jamalbek Tussupov","raw_affiliation_strings":["Department of Information Systems, L.N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-9179-0428","affiliations":[{"raw_affiliation_string":"Department of Information Systems, L.N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066358401","display_name":"\u0410kmaral Kassymova","orcid":"https://orcid.org/0000-0002-4614-4021"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Akmaral Kassymova","raw_affiliation_strings":["Department of Information Technology, Zhangir Khan University, Uralsk 090000, Kazakhstan"],"raw_orcid":"https://orcid.org/0000-0002-4614-4021","affiliations":[{"raw_affiliation_string":"Department of Information Technology, Zhangir Khan University, Uralsk 090000, Kazakhstan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040046835","display_name":"Ayagoz Mukhanova","orcid":"https://orcid.org/0000-0003-3987-0938"},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":true,"raw_author_name":"Ayagoz Mukhanova","raw_affiliation_strings":["Department of Information Systems, L.N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, L.N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075997698","display_name":"Assyl Bissengaliyeva","orcid":"https://orcid.org/0000-0002-6914-2352"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Assyl Bissengaliyeva","raw_affiliation_strings":["Department of Information Technology, Zhangir Khan University, Uralsk 090000, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Zhangir Khan University, Uralsk 090000, Kazakhstan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065707746","display_name":"Zhanar Azhibekova","orcid":"https://orcid.org/0000-0002-4396-1261"},"institutions":[{"id":"https://openalex.org/I191378831","display_name":"Kazakh National Medical University","ror":"https://ror.org/05pc6w891","country_code":"KZ","type":"education","lineage":["https://openalex.org/I191378831"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Zhanar Azhibekova","raw_affiliation_strings":["Department of Information and Communication Technologies, Non-Profit Joint Stock Company S. Asfendiyarov Kazakh National Medical University, Almaty 050000, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technologies, Non-Profit Joint Stock Company S. Asfendiyarov Kazakh National Medical University, Almaty 050000, Kazakhstan","institution_ids":["https://openalex.org/I191378831"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078986051","display_name":"Moldir Yessenova","orcid":"https://orcid.org/0000-0002-2644-0966"},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Moldir Yessenova","raw_affiliation_strings":["Department of Information Systems, L.N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, L.N. Gumilyov Eurasian National University, Astana 010000, Kazakhstan","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073660415","display_name":"Zhanargul Abuova","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhanargul Abuova","raw_affiliation_strings":["Department of Information Technology, Zhangir Khan University, Uralsk 090000, Kazakhstan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Technology, Zhangir Khan University, Uralsk 090000, Kazakhstan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040046835","https://openalex.org/A5066358401"],"corresponding_institution_ids":["https://openalex.org/I10232997"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":4.3565,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.93899596,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"18","issue":"5","first_page":"289","last_page":"289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.993399977684021,"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":0.993399977684021,"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":0.9894999861717224,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9886000156402588,"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":0.7179471254348755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6084845662117004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47092241048812866},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42179161310195923},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3556579649448395},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3365260660648346}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7179471254348755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6084845662117004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47092241048812866},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42179161310195923},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3556579649448395},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3365260660648346}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/a18050289","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18050289","pdf_url":"https://www.mdpi.com/1999-4893/18/5/289/pdf?version=1747635461","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:385304583d0743eb83503d2d8407cf86","is_oa":true,"landing_page_url":"https://doaj.org/article/385304583d0743eb83503d2d8407cf86","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":"Algorithms, Vol 18, Iss 5, p 289 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/a18050289","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a18050289","pdf_url":"https://www.mdpi.com/1999-4893/18/5/289/pdf?version=1747635461","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410481024.pdf","grobid_xml":"https://content.openalex.org/works/W4410481024.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2805117413","https://openalex.org/W2956394034","https://openalex.org/W2959503725","https://openalex.org/W2999786665","https://openalex.org/W3110208794","https://openalex.org/W3126027621","https://openalex.org/W3132939488","https://openalex.org/W3136003884","https://openalex.org/W4206390275","https://openalex.org/W4206935846","https://openalex.org/W4297509747","https://openalex.org/W4307321238","https://openalex.org/W4310494058","https://openalex.org/W4313327571","https://openalex.org/W4319159759","https://openalex.org/W4319444320","https://openalex.org/W4322504929","https://openalex.org/W4323545743","https://openalex.org/W4363650848","https://openalex.org/W4365452597","https://openalex.org/W4367046780","https://openalex.org/W4376874306","https://openalex.org/W4382130836","https://openalex.org/W4384981928","https://openalex.org/W4387782510","https://openalex.org/W4390755813","https://openalex.org/W4392960807","https://openalex.org/W4396685186","https://openalex.org/W4399133461","https://openalex.org/W4404658388","https://openalex.org/W6860348102"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2158836806","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"This":[0],"article":[1,42],"presents":[2],"a":[3,95],"comprehensive":[4],"review":[5],"of":[6,49,78,87,110,148,195,209,235,239],"short":[7,92,200,240],"text":[8,176,219],"clustering":[9,91,177,196],"using":[10],"state-of-the-art":[11],"methods:":[12],"Bidirectional":[13],"Encoder":[14],"Representations":[15],"from":[16],"Transformers":[17],"(BERT),":[18],"Term":[19],"Frequency-Inverse":[20],"Document":[21],"Frequency":[22],"(TF-IDF),":[23],"and":[24,52,55,115,129,156,193,202,214,221,246],"the":[25,46,85,99,111,123,136,152,166,185,187,190,233,236],"novel":[26],"hybrid":[27,100,167],"method":[28,173],"Latent":[29],"Dirichlet":[30],"Allocation":[31],"+":[32,34,37,39,102,104,169,171],"BERT":[33,38,57,103,170],"Autoencoder":[35],"(LDA":[36],"AE).":[40],"The":[41,81,145,162,207,228],"begins":[43],"by":[44,231],"outlining":[45],"theoretical":[47],"foundation":[48],"each":[50],"technique":[51],"its":[53,61,74],"merits":[54],"limitations.":[56],"is":[58,71],"critiqued":[59],"for":[60,73,198,242],"ability":[62],"to":[63,132,180],"understand":[64],"word":[65],"dependence":[66],"in":[67,76,90,212],"text,":[68],"while":[69],"TF-IDF":[70],"lauded":[72],"applicability":[75],"terms":[77],"importance":[79,234],"assessment.":[80],"experimental":[82],"section":[83],"compares":[84],"efficacy":[86],"these":[88,149,210],"methods":[89,197,211],"texts,":[93],"with":[94,159],"specific":[96],"focus":[97],"on":[98,184],"LDA":[101,168],"AE":[105,172],"approach.":[106],"A":[107],"detailed":[108],"examination":[109],"LDA-BERT":[112],"model\u2019s":[113,153],"training":[114],"validation":[116],"loss":[117,124],"over":[118],"200":[119],"epochs":[120],"shows":[121],"that":[122,165],"values":[125],"start":[126],"above":[127],"1.2":[128],"quickly":[130],"decrease":[131],"around":[133],"0.8":[134],"within":[135],"first":[137],"25":[138],"epochs,":[139],"eventually":[140],"stabilizing":[141],"at":[142],"approximately":[143],"0.4.":[144],"close":[146],"alignment":[147],"curves":[150],"suggests":[151],"practical":[154],"learning":[155],"generalization":[157],"capabilities,":[158],"minimal":[160],"overfitting.":[161],"study":[163,188,229],"demonstrates":[164],"significantly":[174],"enhances":[175],"quality":[178],"compared":[179],"individual":[181],"methods.":[182],"Based":[183],"findings,":[186],"recommends":[189],"optimum":[191],"choice":[192],"use":[194],"different":[199],"texts":[201,241],"natural":[203],"language":[204],"processing":[205],"operations.":[206],"applications":[208],"industrial":[213],"educational":[215],"settings,":[216],"where":[217],"successful":[218],"handling":[220,238],"categorization":[222],"are":[223,225],"critical,":[224],"also":[226],"addressed.":[227],"ends":[230],"emphasizing":[232],"holistic":[237],"deeper":[243],"semantic":[244],"comprehension":[245],"effective":[247],"information":[248],"retrieval.":[249]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-19T15:00:24.278416","created_date":"2025-10-10T00:00:00"}