{"id":"https://openalex.org/W4410968111","doi":"https://doi.org/10.1007/s11227-025-07414-4","title":"Optimizing SBERT for long text clustering: two novel approaches with empirical insights","display_name":"Optimizing SBERT for long text clustering: two novel approaches with empirical insights","publication_year":2025,"publication_date":"2025-06-02","ids":{"openalex":"https://openalex.org/W4410968111","doi":"https://doi.org/10.1007/s11227-025-07414-4"},"language":"en","primary_location":{"id":"doi:10.1007/s11227-025-07414-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-025-07414-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-07414-4.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-07414-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054854243","display_name":"Yasin Ortakc\u0131","orcid":"https://orcid.org/0000-0002-0683-2049"},"institutions":[{"id":"https://openalex.org/I173761726","display_name":"Karab\u00fck University","ror":"https://ror.org/04wy7gp54","country_code":"TR","type":"education","lineage":["https://openalex.org/I173761726"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Yasin Ortakci","raw_affiliation_strings":["Department of Computer Engineering, Karabuk University, Demir \u00c7elik Kamp\u00fcs\u00fc, 78050, Merkez, Karab\u00fck, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Karabuk University, Demir \u00c7elik Kamp\u00fcs\u00fc, 78050, Merkez, Karab\u00fck, Turkey","institution_ids":["https://openalex.org/I173761726"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5117805872","display_name":"Burak Borhan","orcid":null},"institutions":[{"id":"https://openalex.org/I173761726","display_name":"Karab\u00fck University","ror":"https://ror.org/04wy7gp54","country_code":"TR","type":"education","lineage":["https://openalex.org/I173761726"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Burak Borhan","raw_affiliation_strings":["Department of Computer Engineering, Karabuk University, Demir \u00c7elik Kamp\u00fcs\u00fc, 78050, Merkez, Karab\u00fck, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Karabuk University, Demir \u00c7elik Kamp\u00fcs\u00fc, 78050, Merkez, Karab\u00fck, Turkey","institution_ids":["https://openalex.org/I173761726"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5054854243"],"corresponding_institution_ids":["https://openalex.org/I173761726"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":13.4373,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":{"value":0.98591461,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"81","issue":"8","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983999729156494,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9934999942779541,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9010094404220581},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6761155128479004},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.4942917823791504},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3920590281486511},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35755831003189087},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.35390233993530273},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.35122132301330566},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3264366388320923},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.0694948136806488}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9010094404220581},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6761155128479004},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.4942917823791504},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3920590281486511},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35755831003189087},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.35390233993530273},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.35122132301330566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3264366388320923},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0694948136806488},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11227-025-07414-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-025-07414-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-07414-4.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11227-025-07414-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11227-025-07414-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11227-025-07414-4.pdf","source":{"id":"https://openalex.org/S32326811","display_name":"The Journal of Supercomputing","issn_l":"0920-8542","issn":["0920-8542","1573-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Journal of Supercomputing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326538","display_name":"Karab\u00fck \u00dcniversitesi","ror":"https://ror.org/04wy7gp54"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410968111.pdf","grobid_xml":"https://content.openalex.org/works/W4410968111.grobid-xml"},"referenced_works_count":59,"referenced_works":["https://openalex.org/W1560851690","https://openalex.org/W1566289585","https://openalex.org/W1981276685","https://openalex.org/W2000117996","https://openalex.org/W2011430131","https://openalex.org/W2250539671","https://openalex.org/W2334175399","https://openalex.org/W2353001802","https://openalex.org/W2474983390","https://openalex.org/W2493916176","https://openalex.org/W2507698410","https://openalex.org/W2576754561","https://openalex.org/W2624904683","https://openalex.org/W2778443828","https://openalex.org/W2803176955","https://openalex.org/W2941126376","https://openalex.org/W2946787236","https://openalex.org/W2962784628","https://openalex.org/W2963026768","https://openalex.org/W2963918774","https://openalex.org/W2964938584","https://openalex.org/W2970641574","https://openalex.org/W2970771703","https://openalex.org/W2988217457","https://openalex.org/W3001219191","https://openalex.org/W3003436681","https://openalex.org/W3008736151","https://openalex.org/W3010633554","https://openalex.org/W3022955783","https://openalex.org/W3070760781","https://openalex.org/W3089862520","https://openalex.org/W3092314298","https://openalex.org/W3128465392","https://openalex.org/W3184324824","https://openalex.org/W3198812502","https://openalex.org/W4213018796","https://openalex.org/W4221014796","https://openalex.org/W4224276467","https://openalex.org/W4292858715","https://openalex.org/W4307561862","https://openalex.org/W4307633137","https://openalex.org/W4309779868","https://openalex.org/W4312188045","https://openalex.org/W4327919569","https://openalex.org/W4361791341","https://openalex.org/W4366771357","https://openalex.org/W4383215352","https://openalex.org/W4385570706","https://openalex.org/W4387693259","https://openalex.org/W4389001310","https://openalex.org/W4389493320","https://openalex.org/W4391926258","https://openalex.org/W4399130767","https://openalex.org/W4401706794","https://openalex.org/W4405412791","https://openalex.org/W6600424091","https://openalex.org/W6601211009","https://openalex.org/W6603042284","https://openalex.org/W6702248584"],"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/W2393816671","https://openalex.org/W2083665254","https://openalex.org/W2942177010"],"abstract_inverted_index":{"Abstract":[0],"Transformer-based":[1],"Large":[2],"Language":[3],"Models":[4],"(LLMs),":[5],"which":[6,27,61],"have":[7,11,85],"recently":[8],"gained":[9],"popularity,":[10],"significantly":[12],"impacted":[13],"the":[14,30,123,147,160,166,178,191,204],"various":[15,138],"fields":[16],"of":[17,22,125,162,186,208],"natural":[18],"language":[19],"processing.":[20],"One":[21,55],"them":[23],"is":[24,58],"text":[25,43,81,195,205],"clustering,":[26],"involves":[28],"categorizing":[29],"huge":[31],"texts":[32,74,101],"produced":[33],"by":[34],"today\u2019s":[35],"digital":[36],"world":[37],"into":[38,79,203],"meaningful":[39,90],"groups.":[40],"LLMs":[41],"enable":[42],"clustering":[44,129,172,184,206],"with":[45,99,137],"a":[46,182],"more":[47],"semantic":[48,67],"and":[49,121,141,168,217],"contextualized":[50],"approach":[51],"than":[52,190],"traditional":[53],"methods.":[54],"such":[56],"model":[57],"Sentence-BERT":[59],"(SBERT),":[60],"has":[62],"been":[63],"modified":[64],"to":[65,76,117,146,171,188],"detect":[66],"similarity":[68],"between":[69],"texts.":[70,156],"Before":[71],"being":[72],"clustered,":[73],"need":[75],"be":[77],"transformed":[78],"numerical":[80],"embeddings.":[82,92],"SBERT-based":[83],"models":[84,127,167],"shown":[86],"promise":[87],"in":[88,194],"generating":[89],"sentence":[91],"However,":[93],"they":[94],"face":[95],"limitations":[96,120],"when":[97],"dealing":[98],"long":[100,130],"that":[102,177],"exceed":[103],"their":[104,142,169],"maximum":[105],"token":[106],"limit.":[107],"In":[108],"this":[109,111,198],"context,":[110],"study":[112,158,199],"proposes":[113],"two":[114],"distinct":[115],"methods":[116,134,164,180],"overcome":[118],"these":[119,163],"enhance":[122],"performance":[124,185,207],"SBERT":[126,139,209],"for":[128,214],"text.":[131],"The":[132,174],"proposed":[133,179],"are":[135,144],"combined":[136],"models,":[140,210],"combinations":[143],"compared":[145],"existing":[148],"default":[149,192],"method":[150,193],"on":[151,165],"three":[152],"datasets":[153],"containing":[154],"lengthy":[155],"This":[157],"evaluates":[159],"impact":[161],"contributions":[170],"performance.":[173],"findings":[175],"indicate":[176],"exhibit":[181],"higher":[183],"up":[187],"14%":[189],"clustering.":[196],"Additionally,":[197],"provides":[200],"valuable":[201],"insights":[202],"offering":[211],"practical":[212],"implications":[213],"further":[215],"research":[216],"applications.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}