{"id":"https://openalex.org/W4404782015","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.534","title":"RoBERT2VecTM: A Novel Approach for Topic Extraction in Islamic Studies","display_name":"RoBERT2VecTM: A Novel Approach for Topic Extraction in Islamic Studies","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4404782015","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.534"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.534","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.534","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.534","pdf_url":"https://aclanthology.org/2024.findings-emnlp.534.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2024.findings-emnlp.534.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114847571","display_name":"Sania Aftar","orcid":"https://orcid.org/0000-0001-8151-8941","observed_orcids":["https://orcid.org/0000-0001-8151-8941"]},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sania Aftar","raw_affiliation_strings":["University of Modena and Reggio Emilia , Modena , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia , Modena , Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036760548","display_name":"Luca Gagliardelli","orcid":"https://orcid.org/0000-0001-5977-1078","observed_orcids":["https://orcid.org/0000-0001-5977-1078"]},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Luca Gagliardelli","raw_affiliation_strings":["University of Modena and Reggio Emilia , Modena , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia , Modena , Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114847572","display_name":"Amina El Ganadi","orcid":"https://orcid.org/0000-0002-8196-2628","observed_orcids":["https://orcid.org/0000-0002-8196-2628"]},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]},{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Amina El Ganadi","raw_affiliation_strings":["University of Modena and Reggio Emilia , Modena , Italy","University of Palermo , Palermo , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia , Modena , Italy","institution_ids":["https://openalex.org/I122346577"]},{"raw_affiliation_string":"University of Palermo , Palermo , Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087367537","display_name":"Federico Ruozzi","orcid":"https://orcid.org/0000-0003-2729-5016","observed_orcids":["https://orcid.org/0000-0003-2729-5016"]},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Federico Ruozzi","raw_affiliation_strings":["University of Modena and Reggio Emilia , Modena , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia , Modena , Italy","institution_ids":["https://openalex.org/I122346577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037830808","display_name":"Sonia Bergamaschi","orcid":"https://orcid.org/0000-0001-8087-6587","observed_orcids":["https://orcid.org/0000-0001-8087-6587"]},"institutions":[{"id":"https://openalex.org/I122346577","display_name":"University of Modena and Reggio Emilia","ror":"https://ror.org/02d4c4y02","country_code":"IT","type":"education","lineage":["https://openalex.org/I122346577"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Sonia Bergamaschi","raw_affiliation_strings":["University of Modena and Reggio Emilia , Modena , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Modena and Reggio Emilia , Modena , Italy","institution_ids":["https://openalex.org/I122346577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8662,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75288419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"9148","last_page":"9158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9868000149726868,"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":0.9868000149726868,"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":0.006500000134110451,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.002400000113993883,"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-modeling","display_name":"topic modeling","score":0.8859999775886536},{"id":"https://openalex.org/keywords/hadith","display_name":"hadith","score":0.8389999866485596},{"id":"https://openalex.org/keywords/arabic-text-analysis","display_name":"Arabic text analysis","score":0.6349999904632568},{"id":"https://openalex.org/keywords/roberta","display_name":"RoBERTa","score":0.8899999856948853},{"id":"https://openalex.org/keywords/doc2vec","display_name":"Doc2Vec","score":0.9800000190734863},{"id":"https://openalex.org/keywords/islamic-studies","display_name":"Islamic studies","score":0.5720000267028809},{"id":"https://openalex.org/keywords/lemmatization","display_name":"lemmatization","score":0.8579999804496765},{"id":"https://openalex.org/keywords/stop-word-removal","display_name":"stop word removal","score":0.9549999833106995},{"id":"https://openalex.org/keywords/arabic-morphology","display_name":"Arabic morphology","score":0.6110000014305115}],"concepts":[{"id":"https://openalex.org/C4445939","wikidata":"https://www.wikidata.org/wiki/Q432","display_name":"Islam","level":2,"score":0.6938298344612122},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5968733429908752},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5397835969924927},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.16556045413017273},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.11027467250823975},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09187677502632141},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0823008120059967}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2024.findings-emnlp.534","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.534","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.534","pdf_url":"https://aclanthology.org/2024.findings-emnlp.534.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniecampus.it:11389/69844","doi":null,"is_oa":false,"landing_page_url":"https://hdl.handle.net/11389/69844","pdf_url":null,"source":{"id":"https://openalex.org/S4306400077","display_name":"IRIS eCampus Telematic University (Universit\u00e0 degli Studi eCampus)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I167322064","host_organization_name":"Universit\u00e0 degli Studi eCampus","host_organization_lineage":["https://openalex.org/I167322064"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.unimore.it:11380/1363506","doi":null,"is_oa":true,"landing_page_url":"https://hdl.handle.net/11380/1363506","pdf_url":null,"source":{"id":"https://openalex.org/S4306400718","display_name":"IRIS UNIMORE (University of Modena and Reggio Emilia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I122346577","host_organization_name":"University of Modena and Reggio Emilia","host_organization_lineage":["https://openalex.org/I122346577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-emnlp.534","doi":"https://doi.org/10.18653/v1/2024.findings-emnlp.534","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-emnlp.534","pdf_url":"https://aclanthology.org/2024.findings-emnlp.534.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404782015.pdf","grobid_xml":"https://content.openalex.org/works/W4404782015.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7021240355","https://openalex.org/W7043716090","https://openalex.org/W7168296544","https://openalex.org/W7106694360","https://openalex.org/W2921538177","https://openalex.org/W4406165370","https://openalex.org/W7115612680","https://openalex.org/W4412130305","https://openalex.org/W4409142187","https://openalex.org/W4320083566"],"abstract_inverted_index":{"Investigating":[0],"\"Hadith\"":[1],"texts,":[2],"crucial":[3],"for":[4,94,132],"theological":[5],"studies":[6,40],"and":[7,84,111,128],"Islamic":[8],"jurisprudence,":[9],"presents":[10],"challenges":[11,34],"due":[12],"to":[13,31,125],"the":[14,33,43,57,65,90,98,106,133],"linguistic":[15],"complexity":[16],"of":[17,35,68,89,100,109,136],"Arabic,":[18],"such":[19],"as":[20],"its":[21],"complex":[22,137],"morphology.In":[23],"this":[24],"paper,":[25],"we":[26],"propose":[27],"an":[28],"innovative":[29],"approach":[30,54],"address":[32],"topic":[36,115],"modeling":[37],"in":[38,113,122],"Hadith":[39],"by":[41,80],"utilizing":[42],"Contextualized":[44],"Topic":[45],"Model":[46],"(CTM).Our":[47],"study":[48],"introduces":[49],"RoBERT2VecTM,":[50],"a":[51,119],"novel":[52],"neural-based":[53],"that":[55],"combines":[56],"RoBERTa":[58],"transformer":[59],"model":[60],"with":[61],"Doc2Vec,":[62],"specifically":[63],"targeting":[64],"semantic":[66],"analysis":[67,135],"\"Matn\"":[69],"(the":[70],"actual":[71],"content).The":[72],"methodology":[73],"outperforms":[74],"many":[75],"traditional":[76],"state-of-the-art":[77],"NLP":[78,124],"models":[79],"generating":[81],"more":[82],"coherent":[83],"diverse":[85],"Arabic":[86],"topics.The":[87],"diversity":[88],"generated":[91],"topics":[92],"allows":[93],"further":[95],"categorization,":[96],"deepening":[97],"understanding":[99],"discussed":[101],"concepts.Notably,":[102],"our":[103],"research":[104],"highlights":[105],"critical":[107],"impact":[108],"lemmatization":[110],"stopwords":[112],"enhancing":[114],"modeling.This":[116],"breakthrough":[117],"marks":[118],"significant":[120],"stride":[121],"applying":[123],"non-Latin":[126],"languages":[127],"opens":[129],"new":[130],"avenues":[131],"nuanced":[134],"religious":[138],"texts.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2024-11-28T00:00:00"}