{"id":"https://openalex.org/W7224652107","doi":"https://doi.org/10.3390/make8110359","title":"Encoder Mixing for Unsupervised Topic Discovery in Multi-Platform Chat: An Exploratory Study on Proxy Corpora","display_name":"Encoder Mixing for Unsupervised Topic Discovery in Multi-Platform Chat: An Exploratory Study on Proxy Corpora","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224652107","doi":"https://doi.org/10.3390/make8110359"},"language":"en","primary_location":{"id":"doi:10.3390/make8110359","doi":"https://doi.org/10.3390/make8110359","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8110359","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","poland-20","russia-white-list-1"],"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":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.3390/make8110359","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114815466","display_name":"Rajon Bardhan","orcid":"https://orcid.org/0009-0006-0706-9643","observed_orcids":["https://orcid.org/0009-0006-0706-9643"]},"institutions":[{"id":"https://openalex.org/I25041050","display_name":"Augusta University","ror":"https://ror.org/012mef835","country_code":"US","type":"education","lineage":["https://openalex.org/I25041050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rajon Bardhan","raw_affiliation_strings":["School of Computer and Cyber Sciences, Augusta University, Augusta, GA 30904, USA"],"raw_orcid":"https://orcid.org/0009-0006-0706-9643","affiliations":[{"raw_affiliation_string":"School of Computer and Cyber Sciences, Augusta University, Augusta, GA 30904, USA","institution_ids":["https://openalex.org/I25041050"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160105572","display_name":"Venkat Sumanth","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venkat Sumanth","raw_affiliation_strings":["Department of Computer Science, Florida State University, Tallahassee, FL 32306, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Florida State University, Tallahassee, FL 32306, USA","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085777000","display_name":"Gokila Dorai","orcid":"https://orcid.org/0000-0001-5825-7034","observed_orcids":["https://orcid.org/0000-0001-5825-7034"]},"institutions":[{"id":"https://openalex.org/I25041050","display_name":"Augusta University","ror":"https://ror.org/012mef835","country_code":"US","type":"education","lineage":["https://openalex.org/I25041050"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gokila Dorai","raw_affiliation_strings":["School of Computer and Cyber Sciences, Augusta University, Augusta, GA 30904, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Cyber Sciences, Augusta University, Augusta, GA 30904, USA","institution_ids":["https://openalex.org/I25041050"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060783083","display_name":"Pramesh Regmi","orcid":"https://orcid.org/0009-0001-1488-4359","observed_orcids":["https://orcid.org/0009-0001-1488-4359"]},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pramesh Regmi","raw_affiliation_strings":["Department of Computer Science, Florida State University, Tallahassee, FL 32306, USA"],"raw_orcid":"https://orcid.org/0009-0001-1488-4359","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Florida State University, Tallahassee, FL 32306, USA","institution_ids":["https://openalex.org/I103163165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160141165","display_name":"Piyush Kumar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I103163165","display_name":"Florida State University","ror":"https://ror.org/05g3dte14","country_code":"US","type":"education","lineage":["https://openalex.org/I103163165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Piyush Kumar","raw_affiliation_strings":["Department of Computer Science, Florida State University, Tallahassee, FL 32306, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Florida State University, Tallahassee, FL 32306, USA","institution_ids":["https://openalex.org/I103163165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085777000"],"corresponding_institution_ids":["https://openalex.org/I25041050"],"apc_list":{"value":1800,"currency":"CHF","value_usd":2172},"apc_paid":{"value":1800,"currency":"CHF","value_usd":2172},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85554649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":"11","first_page":"359","last_page":"359"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9556000232696533,"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":0.9556000232696533,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.02019999921321869,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.00570000009611249,"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/chat-analysis","display_name":"chat analysis","score":0.5699999928474426},{"id":"https://openalex.org/keywords/scope","display_name":"scope","score":0.6940000057220459},{"id":"https://openalex.org/keywords/semantic-coherence","display_name":"semantic coherence","score":0.38100001215934753},{"id":"https://openalex.org/keywords/topic-clustering","display_name":"topic clustering","score":0.4309999942779541},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8001000285148621},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6276000142097473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6121000051498413},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6090999841690063},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48739999532699585},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.47380000352859497},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.3734000027179718},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.366100013256073},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3474999964237213},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.3416000008583069},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C2780276568","wikidata":"https://www.wikidata.org/wiki/Q191928","display_name":"Polysemy","level":2,"score":0.3158000111579895},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27880001068115234},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.25999999046325684},{"id":"https://openalex.org/C37381756","wikidata":"https://www.wikidata.org/wiki/Q20203288","display_name":"Representativeness heuristic","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3390/make8110359","doi":"https://doi.org/10.3390/make8110359","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8110359","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","poland-20","russia-white-list-1"],"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":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.3390/make8110359","doi":"https://doi.org/10.3390/make8110359","is_oa":true,"landing_page_url":"https://doi.org/10.3390/make8110359","pdf_url":null,"source":{"id":"https://openalex.org/S4210213891","display_name":"Machine Learning and Knowledge Extraction","issn_l":"2504-4990","issn":["2504-4990"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","jufo-1","norway-1","poland-20","russia-white-list-1"],"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":"Machine Learning and Knowledge Extraction","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1557074680","https://openalex.org/W1987971958","https://openalex.org/W1988047293","https://openalex.org/W2053154970","https://openalex.org/W2097749765","https://openalex.org/W2159083595","https://openalex.org/W2343957433","https://openalex.org/W2970200208","https://openalex.org/W2970641574","https://openalex.org/W2971569798","https://openalex.org/W3010662135","https://openalex.org/W3128181049","https://openalex.org/W3138773240","https://openalex.org/W3156636935","https://openalex.org/W3172351783","https://openalex.org/W3173618889","https://openalex.org/W3174544005","https://openalex.org/W3176127324","https://openalex.org/W3210858927","https://openalex.org/W4200265438","https://openalex.org/W4213423307","https://openalex.org/W4281714606","https://openalex.org/W4283449072","https://openalex.org/W4293065666","https://openalex.org/W4386576685","https://openalex.org/W4388971394","https://openalex.org/W4400531953","https://openalex.org/W4401043789","https://openalex.org/W4402670856","https://openalex.org/W4402671936","https://openalex.org/W4402811732","https://openalex.org/W4404932432","https://openalex.org/W4408947729","https://openalex.org/W4410702284","https://openalex.org/W4411119336","https://openalex.org/W4412887722","https://openalex.org/W4412944965","https://openalex.org/W4415796369","https://openalex.org/W7110260630","https://openalex.org/W7139055155","https://openalex.org/W7167539925"],"related_works":["https://openalex.org/W2528064063","https://openalex.org/W2921642681","https://openalex.org/W3082103276","https://openalex.org/W3199050644","https://openalex.org/W4401043789","https://openalex.org/W2009961094","https://openalex.org/W7097771230","https://openalex.org/W7130502432","https://openalex.org/W7150743691","https://openalex.org/W6966649665"],"abstract_inverted_index":{"Seized-device":[0],"chat":[1,53],"dumps":[2],"exceed":[3],"manual":[4],"review,":[5],"and":[6,21,27,58,66,99,118,140,205,248],"case-specific":[7],"topic":[8,32,64],"lists":[9],"are":[10,129,226],"not":[11,236],"known":[12],"in":[13,144,239],"advance.":[14],"We":[15],"extend":[16],"SCOPE":[17],"(Semantic":[18],"Coherence":[19],"Pruning":[20],"Extraction),":[22],"which":[23],"embeds":[24],"each":[25,28,180],"message":[26],"of":[29],"21":[30],"predefined":[31],"labels":[33,184],"with":[34,41],"all-MiniLM-L12-v2;":[35],"we":[36],"replace":[37],"that":[38,243],"seed":[39,88],"list":[40],"unsupervised":[42],"discovery.":[43],"The":[44,74,147],"scored":[45],"system":[46],"is":[47,78,94,142],"a":[48,70,102,119,155,160,169,216],"six-stage":[49],"pipeline.":[50],"It":[51],"cuts":[52],"by":[54,154,175],"embedding":[55],"drift,":[56],"clusters":[57],"names":[59],"those":[60,132],"segments,":[61],"builds":[62],"per-user":[63],"timelines,":[65],"scores":[67],"them":[68],"against":[69],"per-message":[71],"reference":[72,181],"column.":[73],"baseline":[75],"cell,":[76],"minilm-l12-v2,":[77],"SCOPE\u2019s":[79],"encoder":[80,92,237],"run":[81],"through":[82],"the":[83,87,115,199,206,227,231],"frozen":[84],"pipeline":[85],"without":[86],"list.":[89],"A":[90,241],"49-cell":[91],"grid":[93,151,202],"attempted":[95],"on":[96,137,198,210],"two":[97],"corpora":[98],"three":[100],"settings:":[101],"66-message":[103],"Sample":[104],"walkthrough":[105],"(4":[106],"topics);":[107],"CrystalClear":[108,148,197],"(917":[109],"messages,":[110,124],"7":[111],"rooms,":[112],"30":[113],"topics),":[114],"independent":[116],"corpus;":[117],"Dataset":[120,207],"3":[121,208],"coreset":[122,209],"(2999":[123],"23":[125],"topics)":[126],"whose":[127],"rankings":[128,222,238],"provisional.":[130],"Of":[131],"49":[133],"cells,":[134],"37":[135],"score":[136],"all":[138,145],"three,":[139],"none":[141],"first":[143,245],"three.":[146],"semantic":[149,200],"hand":[150,201],"was":[152,165],"marked":[153],"large":[156],"language":[157],"model":[158,171],"under":[159,230],"written":[161],"rule,":[162],"then":[163],"it":[164],"revised":[166],"once":[167],"after":[168],"second":[170],"resolved":[172],"open":[173,252],"questions":[174],"reading":[176],"sample":[177],"messages":[178],"carrying":[179],"label;":[182],"five":[183],"changed.":[185],"No":[186],"human":[187],"checked":[188],"individual":[189],"marks.":[190],"UAE-Large-V1":[191],"leads":[192],"both":[193,221],"evidential":[194],"corpora,":[195],"taking":[196],"(overall-F1":[203],"0.674)":[204],"auto":[211],"p90":[212],"(macro-F1":[213],"0.593,":[214],"provisional);":[215],"many-to-one":[217],"definition-matching":[218],"protocol":[219],"reverses":[220],"to":[223],"MiniLM-L6.":[224],"These":[225],"observed":[228],"results":[229],"specific":[232],"evaluation":[233],"procedures":[234],"described,":[235],"general.":[240],"mix":[242],"stays":[244],"across":[246],"matchers":[247],"settings":[249],"remains":[250],"an":[251],"limitation.":[253]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-30T00:00:00"}