{"id":"https://openalex.org/W7134901167","doi":"https://doi.org/10.1109/icdmw69685.2025.00139","title":"New Topic Discovery Using LLM Analysis and Entropy Based Clustering of Short Texts","display_name":"New Topic Discovery Using LLM Analysis and Entropy Based Clustering of Short Texts","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W7134901167","doi":"https://doi.org/10.1109/icdmw69685.2025.00139"},"language":null,"primary_location":{"id":"doi:10.1109/icdmw69685.2025.00139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5128717554","display_name":"Allen Detmer","orcid":null},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Allen Detmer","raw_affiliation_strings":["University of Cincinnati,Department of Computer Science,Cincinnati,OH,USA"],"raw_orcid":"https://orcid.org/0009-0002-1659-8935","affiliations":[{"raw_affiliation_string":"University of Cincinnati,Department of Computer Science,Cincinnati,OH,USA","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039109763","display_name":"Raj Bhatnagar","orcid":null},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raj Bhatnagar","raw_affiliation_strings":["University of Cincinnati,Department of Computer Science,Cincinnati,OH,USA"],"raw_orcid":"https://orcid.org/0000-0001-5222-6800","affiliations":[{"raw_affiliation_string":"University of Cincinnati,Department of Computer Science,Cincinnati,OH,USA","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058109776","display_name":"Jillian Aurisano","orcid":"https://orcid.org/0000-0003-4761-1741"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jillian Aurisano","raw_affiliation_strings":["University of Cincinnati,Department of Computer Science,Cincinnati,OH,USA"],"raw_orcid":"https://orcid.org/0000-0003-4761-1741","affiliations":[{"raw_affiliation_string":"University of Cincinnati,Department of Computer Science,Cincinnati,OH,USA","institution_ids":["https://openalex.org/I63135867"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63135867"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1180","last_page":"1189"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.303600013256073,"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":0.303600013256073,"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":0.17149999737739563,"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/T10028","display_name":"Topic Modeling","score":0.08550000190734863,"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":0.5752999782562256},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4885999858379364},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.3174999952316284},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.30649998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6255999803543091},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5752999782562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5133000016212463},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3822999894618988},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3174999952316284},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29280000925064087},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.26570001244544983}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdmw69685.2025.00139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdmw69685.2025.00139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Data Mining Workshops (ICDMW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7159311175346375,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1971022913","https://openalex.org/W1995875735","https://openalex.org/W2053075547","https://openalex.org/W2096974619","https://openalex.org/W2153233077","https://openalex.org/W2174706414","https://openalex.org/W2579642215","https://openalex.org/W2661359212","https://openalex.org/W2970641574","https://openalex.org/W3005345245","https://openalex.org/W3120426936","https://openalex.org/W4206729245","https://openalex.org/W4384662964","https://openalex.org/W4385245566","https://openalex.org/W4386078164","https://openalex.org/W4389524512","https://openalex.org/W4396814317","https://openalex.org/W4403294972","https://openalex.org/W4403343675","https://openalex.org/W4405838439","https://openalex.org/W4409427893","https://openalex.org/W4411073757","https://openalex.org/W4412876847"],"related_works":[],"abstract_inverted_index":{"Our":[0,72],"goal":[1],"in":[2,70,80,104],"this":[3,129],"paper":[4],"is":[5,42,55],"to":[6,111,117],"process":[7,112],"short-text":[8],"collections,":[9],"labeled":[10,39],"by":[11,26,128],"their":[12,105],"topics,":[13],"and":[14,29,48,84],"identify":[15],"those":[16,30],"groups":[17],"of":[18,51,135],"text":[19,31,40,52,67],"items":[20,32,68],"that":[21,33,57,96],"may":[22,34],"be":[23,35],"better":[24],"characterized":[25],"new":[27,119],"labels":[28,120],"mislabeled.":[36],"When":[37],"a":[38,81,91,101],"collection":[41],"clustered":[43],"based":[44],"on":[45],"the":[46,63,77],"syntactic":[47],"semantic":[49],"contents":[50],"items,":[53],"it":[54],"expected":[56],"each":[58],"cluster":[59],"will":[60],"also":[61],"share":[62],"same":[64],"label":[65,88,106,115],"for":[66,121,131],"contained":[69],"it.":[71],"approach":[73,130],"presented":[74],"here":[75],"embeds":[76],"short":[78,136],"texts":[79],"lower-dimensional":[82],"space":[83],"then,":[85],"using":[86],"spatial":[87,94],"entropy":[89],"as":[90],"guide,":[92],"finds":[93],"clusters":[95,116],"are":[97],"contiguous":[98],"but":[99],"have":[100],"wide":[102],"diversity":[103],"assignments.":[107],"We":[108,123],"use":[109],"LLMs":[110],"such":[113],"impure":[114],"discover":[118],"them.":[122],"demonstrate":[124],"promising":[125],"results":[126],"obtained":[127],"two":[132],"different":[133],"collections":[134],"texts.":[137]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-12T00:00:00"}