{"id":"https://openalex.org/W7117568279","doi":"https://doi.org/10.1109/iisa66859.2025.11311261","title":"S <sup>2</sup> BERTopic \u2013 A Topic Modeling Approach on Semantic Similarity Leveraging BERTopic","display_name":"S <sup>2</sup> BERTopic \u2013 A Topic Modeling Approach on Semantic Similarity Leveraging BERTopic","publication_year":2025,"publication_date":"2025-07-10","ids":{"openalex":"https://openalex.org/W7117568279","doi":"https://doi.org/10.1109/iisa66859.2025.11311261"},"language":null,"primary_location":{"id":"doi:10.1109/iisa66859.2025.11311261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iisa66859.2025.11311261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information, Intelligence, Systems &amp;amp; Applications (IISA)","raw_type":"proceedings-article"},"type":"article","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/A5121562145","display_name":"Dimitrios Tzolas","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dimitrios Tzolas","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064764358","display_name":"Ioannis E. Venetis","orcid":"https://orcid.org/0000-0002-0022-0447"},"institutions":[{"id":"https://openalex.org/I154757721","display_name":"University of Piraeus","ror":"https://ror.org/02qs84g94","country_code":"GR","type":"education","lineage":["https://openalex.org/I154757721"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ioannis E. Venetis","raw_affiliation_strings":["University of Piraeus,Department of Informatics,Piraeus,Greece"],"affiliations":[{"raw_affiliation_string":"University of Piraeus,Department of Informatics,Piraeus,Greece","institution_ids":["https://openalex.org/I154757721"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5121562145"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.84534512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5825999975204468,"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":0.5825999975204468,"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":0.07999999821186066,"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":0.05209999904036522,"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/topic-model","display_name":"Topic model","score":0.6065000295639038},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5648999810218811},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5476999878883362},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.48840001225471497},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.4860000014305115},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.47609999775886536},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.45010000467300415},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.4404999911785126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259000182151794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6141999959945679},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6065000295639038},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5648999810218811},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5586000084877014},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.45010000467300415},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.4404999911785126},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.39890000224113464},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2778828372","wikidata":"https://www.wikidata.org/wiki/Q5283209","display_name":"Distributional semantics","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26440000534057617},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C2777889803","wikidata":"https://www.wikidata.org/wiki/Q25047676","display_name":"Named entity","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iisa66859.2025.11311261","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iisa66859.2025.11311261","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 16th International Conference on Information, Intelligence, Systems &amp;amp; Applications (IISA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2739351760","https://openalex.org/W2911489562","https://openalex.org/W2950681488","https://openalex.org/W2970641574","https://openalex.org/W3021397474","https://openalex.org/W3099950029","https://openalex.org/W3156636935"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"<tex":[3,58],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[4,59],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$S^{2}$</tex>":[5],"BERTopic,":[6],"a":[7,28,41],"novel":[8],"algorithm":[9],"that":[10],"combines":[11],"semantic":[12],"similarity":[13,65],"and":[14,23,51,63,73,91],"topic":[15,56],"modeling":[16],"by":[17],"leveraging":[18],"the":[19,35,77,80],"capabilities":[20],"of":[21,79],"SBERT":[22],"BERTopic.":[24],"The":[25],"method":[26],"introduces":[27],"hybrid":[29],"CPU-GPU":[30],"architecture":[31],"to":[32,40],"efficiently":[33],"retrieve":[34],"most":[36],"semantically":[37,85],"similar":[38],"sentences":[39],"given":[42],"input.":[43],"By":[44],"clustering":[45],"preprocessed":[46],"sentence":[47],"embeddings":[48],"using":[49],"BERTopic":[50],"narrowing":[52],"search":[53],"space":[54],"via":[55],"relevance,":[57],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">$\\mathrm{S}^{2}$</tex>BERTopic":[60],"enables":[61],"accurate":[62],"scalable":[64],"matching.":[66],"Evaluation":[67],"on":[68],"multiple":[69],"datasets\u2014including":[70],"paraphrased,":[71],"summarized,":[72],"densely":[74],"informative":[75],"sentences\u2014demonstrates":[76],"effectiveness":[78],"proposed":[81],"approach":[82],"in":[83],"identifying":[84],"equivalent":[86],"content,":[87],"even":[88],"when":[89],"lexical":[90],"syntactic":[92],"variations":[93],"are":[94],"significant.":[95]},"counts_by_year":[],"updated_date":"2025-12-31T23:11:33.660297","created_date":"2025-12-30T00:00:00"}