{"id":"https://openalex.org/W4409427893","doi":"https://doi.org/10.1109/access.2025.3560543","title":"LLM-Based Topic Modeling for Dark Web Q&A Forums: A Comparative Analysis With Traditional Methods","display_name":"LLM-Based Topic Modeling for Dark Web Q&A Forums: A Comparative Analysis With Traditional Methods","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409427893","doi":"https://doi.org/10.1109/access.2025.3560543"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3560543","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3560543","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3560543","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074070812","display_name":"Luis de\u2010Marcos","orcid":"https://orcid.org/0000-0003-0718-8774"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Luis de-Marcos","raw_affiliation_strings":["Department of Computer Science, University of Alcalá, Alcalá de Henares, Madrid, Spain","Alcalá de Henares, Universidad de Alcalá, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0003-0718-8774","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Alcalá, Alcalá de Henares, Madrid, Spain","institution_ids":["https://openalex.org/I189268942"]},{"raw_affiliation_string":"Alcalá de Henares, Universidad de Alcalá, Madrid, Spain","institution_ids":["https://openalex.org/I189268942"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032586796","display_name":"Adri\u00e1n Dom\u00ednguez\u2010D\u00edaz","orcid":"https://orcid.org/0000-0001-7632-8609"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Adri\u00e1n Dom\u00ednguez-D\u00edaz","raw_affiliation_strings":["Department of Computer Science, University of Alcalá, Alcalá de Henares, Madrid, Spain","Alcalá de Henares, Universidad de Alcalá, Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0001-7632-8609","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Alcalá, Alcalá de Henares, Madrid, Spain","institution_ids":["https://openalex.org/I189268942"]},{"raw_affiliation_string":"Alcalá de Henares, Universidad de Alcalá, Madrid, Spain","institution_ids":["https://openalex.org/I189268942"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I189268942"],"apc_list":{"value":2075,"currency":"USD","value_usd":2075},"apc_paid":{"value":2075,"currency":"USD","value_usd":2075},"fwci":16.2128,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.98823647,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"13","issue":null,"first_page":"67159","last_page":"67169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.9840999841690063,"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"}},"topics":[{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.9840999841690063,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9375,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6681194305419922},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4503466486930847},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4348064959049225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6681194305419922},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4503466486930847},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4348064959049225}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3560543","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3560543","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b17b78e091d44b69873a3ac34e79103d","is_oa":true,"landing_page_url":"https://doaj.org/article/b17b78e091d44b69873a3ac34e79103d","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":"IEEE Access, Vol 13, Pp 67159-67169 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3560543","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3560543","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4878411931","display_name":null,"funder_award_id":"PID2021-125645OB-I00","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W3111233072","https://openalex.org/W4390509863","https://openalex.org/W4391233103","https://openalex.org/W4399725289","https://openalex.org/W4400200247","https://openalex.org/W4401017171","https://openalex.org/W4401748234","https://openalex.org/W4402470663","https://openalex.org/W4402628945","https://openalex.org/W4402820183","https://openalex.org/W4402827081","https://openalex.org/W4404102510","https://openalex.org/W4405083701","https://openalex.org/W4405271227","https://openalex.org/W4405838439","https://openalex.org/W4405907401","https://openalex.org/W4405918213","https://openalex.org/W4406057130","https://openalex.org/W4406715050","https://openalex.org/W4406771630","https://openalex.org/W4406832864","https://openalex.org/W4406945781","https://openalex.org/W4407410551","https://openalex.org/W4407938633","https://openalex.org/W4407953565","https://openalex.org/W4408226958","https://openalex.org/W4408325034","https://openalex.org/W4408327155","https://openalex.org/W4408432785","https://openalex.org/W4408475807","https://openalex.org/W6868171561","https://openalex.org/W6873629399","https://openalex.org/W6883126320","https://openalex.org/W6910453285"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Topic":[0],"modeling":[1,36,212],"is":[2],"a":[3,233],"critical":[4],"tool":[5,235],"for":[6,236],"understanding":[7],"the":[8,20,26,81,103,108,156,162,189,206,216,219,222,225,248],"thematic":[9],"structures":[10],"of":[11,28,83,191,208,218,224],"unstructured":[12,240],"text":[13,220,241],"data,":[14,242],"particularly":[15,243],"in":[16,38,69,124,188,244],"specialized":[17,245],"domains":[18,246],"like":[19,144,247],"dark":[21,40,192,249],"web.":[22,250],"This":[23,227],"study":[24,228],"compares":[25],"effectiveness":[27],"large":[29],"language":[30],"models":[31],"(LLMs)":[32],"and":[33,50,57,63,75,97,105,133,146,150,161,166,173,221,239],"traditional":[34,59,122,136,167],"topic":[35,84,109,211],"techniques":[37,137,213],"analyzing":[39,237],"web":[41,193],"Q&A":[42],"forums,":[43,194],"which":[44],"are":[45,186],"characterized":[46],"by":[47,86,112],"short,":[48],"informal,":[49],"context-specific":[51],"posts.":[52],"We":[53],"evaluate":[54],"two":[55],"LLMs\u2014GPT":[56],"Gemini\u2014against":[58],"methods,":[60],"TF-IDF":[61],"(scikit-learn)":[62],"Latent":[64],"Dirichlet":[65],"Allocation":[66],"(LDA,":[67],"Gensim),":[68],"their":[70,184,230],"ability":[71],"to":[72],"generate":[73],"meaningful":[74],"coherent":[76],"topics.":[77,93],"Additionally,":[78],"we":[79,101],"explore":[80],"impact":[82],"granularity":[85],"comparing":[87],"GPT":[88],"single-word":[89,172,200],"topics":[90,175,201],"with":[91],"two-word":[92,174,179],"Using":[94],"semantic":[95],"similarity":[96,149],"Levenshtein":[98,151],"distance":[99,152],"metrics,":[100],"quantify":[102],"alignment":[104,158],"divergence":[106,163],"between":[107,159,164,171],"representations":[110],"produced":[111],"these":[113],"methods.":[114,168],"Our":[115],"findings":[116],"demonstrate":[117],"that":[118,177],"LLMs":[119,160,165],"consistently":[120],"outperform":[121],"methods":[123],"capturing":[125],"contextually":[126],"relevant":[127],"themes,":[128],"such":[129],"as":[130,232],"\"scam,\"":[131],"\"bitcoin,\"":[132],"\"hacking,\"":[134],"while":[135,178],"often":[138,198],"produce":[139],"generic":[140],"or":[141],"non-topical":[142],"terms":[143],"\"questions\"":[145],"\"know.\"":[147],"Semantic":[148],"metrics":[153],"further":[154],"highlight":[155],"strong":[157],"The":[169],"comparison":[170],"reveals":[176],"labels":[180],"offer":[181],"additional":[182],"nuance,":[183],"benefits":[185],"limited":[187],"context":[190],"where":[195],"concise":[196],"posts":[197],"make":[199],"sufficient.":[202],"These":[203],"results":[204],"underscore":[205],"importance":[207],"selecting":[209],"appropriate":[210],"based":[214],"on":[215],"characteristics":[217],"requirements":[223],"analysis.":[226],"highlights":[229],"potential":[231],"valuable":[234],"complex":[238]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-04-15T00:00:00"}