{"id":"https://openalex.org/W4390048648","doi":"https://doi.org/10.3390/info15010008","title":"Offensive Text Span Detection in Romanian Comments Using Large Language Models","display_name":"Offensive Text Span Detection in Romanian Comments Using Large Language Models","publication_year":2023,"publication_date":"2023-12-21","ids":{"openalex":"https://openalex.org/W4390048648","doi":"https://doi.org/10.3390/info15010008"},"language":"en","primary_location":{"id":"doi:10.3390/info15010008","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15010008","pdf_url":"https://www.mdpi.com/2078-2489/15/1/8/pdf?version=1703168330","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/15/1/8/pdf?version=1703168330","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079424084","display_name":"Andrei Paraschiv","orcid":"https://orcid.org/0000-0002-7992-4227"},"institutions":[{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Andrei Paraschiv","raw_affiliation_strings":["Computer Science and Engineering Department, National University of Science and Technology Politehnica of Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania"],"raw_orcid":"https://orcid.org/0000-0002-7992-4227","affiliations":[{"raw_affiliation_string":"Computer Science and Engineering Department, National University of Science and Technology Politehnica of Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093549308","display_name":"Teodora Andreea Ion","orcid":"https://orcid.org/0009-0005-6511-4468"},"institutions":[{"id":"https://openalex.org/I33800924","display_name":"Academia Oamenilor de \u0218tiin\u021b\u0103 din Rom\u00e2nia","ror":"https://ror.org/04ybnj478","country_code":"RO","type":"facility","lineage":["https://openalex.org/I33800924"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Teodora Andreea Ion","raw_affiliation_strings":["Academy of Romanian Scientists, Str. Ilfov, Nr. 3, 050044 Bucharest, Romania"],"raw_orcid":"https://orcid.org/0009-0005-6511-4468","affiliations":[{"raw_affiliation_string":"Academy of Romanian Scientists, Str. Ilfov, Nr. 3, 050044 Bucharest, Romania","institution_ids":["https://openalex.org/I33800924"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072192995","display_name":"Mihai Dasc\u0103lu","orcid":"https://orcid.org/0000-0002-4815-9227"},"institutions":[{"id":"https://openalex.org/I33800924","display_name":"Academia Oamenilor de \u0218tiin\u021b\u0103 din Rom\u00e2nia","ror":"https://ror.org/04ybnj478","country_code":"RO","type":"facility","lineage":["https://openalex.org/I33800924"]},{"id":"https://openalex.org/I61641377","display_name":"Universitatea Na\u021bional\u0103 de \u0218tiin\u021b\u0103 \u0219i Tehnologie Politehnica Bucure\u0219ti","ror":"https://ror.org/0558j5q12","country_code":"RO","type":"education","lineage":["https://openalex.org/I61641377"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Mihai Dascalu","raw_affiliation_strings":["Academy of Romanian Scientists, Str. Ilfov, Nr. 3, 050044 Bucharest, Romania","Computer Science and Engineering Department, National University of Science and Technology Politehnica of Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania"],"raw_orcid":"https://orcid.org/0000-0002-4815-9227","affiliations":[{"raw_affiliation_string":"Academy of Romanian Scientists, Str. Ilfov, Nr. 3, 050044 Bucharest, Romania","institution_ids":["https://openalex.org/I33800924"]},{"raw_affiliation_string":"Computer Science and Engineering Department, National University of Science and Technology Politehnica of Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania","institution_ids":["https://openalex.org/I61641377"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072192995"],"corresponding_institution_ids":["https://openalex.org/I33800924","https://openalex.org/I61641377"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.7046,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75793419,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"15","issue":"1","first_page":"8","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9988999962806702,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9988999962806702,"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/offensive","display_name":"Offensive","score":0.9838715195655823},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6502221822738647},{"id":"https://openalex.org/keywords/romanian","display_name":"Romanian","score":0.5007729530334473},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.49964261054992676},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4787237346172333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41965121030807495},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39906883239746094},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.27423688769340515},{"id":"https://openalex.org/keywords/operations-research","display_name":"Operations research","score":0.17787030339241028},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15962505340576172}],"concepts":[{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.9838715195655823},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6502221822738647},{"id":"https://openalex.org/C129400051","wikidata":"https://www.wikidata.org/wiki/Q7913","display_name":"Romanian","level":2,"score":0.5007729530334473},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.49964261054992676},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4787237346172333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41965121030807495},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39906883239746094},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.27423688769340515},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.17787030339241028},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15962505340576172},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info15010008","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15010008","pdf_url":"https://www.mdpi.com/2078-2489/15/1/8/pdf?version=1703168330","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:1eaac3fe43d7498e8e0e36f0962be2f6","is_oa":true,"landing_page_url":"https://doaj.org/article/1eaac3fe43d7498e8e0e36f0962be2f6","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":"Information, Vol 15, Iss 1, p 8 (2023)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info15010008","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info15010008","pdf_url":"https://www.mdpi.com/2078-2489/15/1/8/pdf?version=1703168330","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4390048648.pdf"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W1638659076","https://openalex.org/W1815076433","https://openalex.org/W2003756175","https://openalex.org/W2047449974","https://openalex.org/W2571312737","https://openalex.org/W2595653137","https://openalex.org/W2604821579","https://openalex.org/W2885170888","https://openalex.org/W2890727387","https://openalex.org/W2912105690","https://openalex.org/W2949676527","https://openalex.org/W2962977603","https://openalex.org/W2963481894","https://openalex.org/W2963943967","https://openalex.org/W2964347220","https://openalex.org/W2970487286","https://openalex.org/W2970641574","https://openalex.org/W2973806433","https://openalex.org/W3000571327","https://openalex.org/W3014459433","https://openalex.org/W3035390927","https://openalex.org/W3046087842","https://openalex.org/W3092234077","https://openalex.org/W3101574506","https://openalex.org/W3105113320","https://openalex.org/W3114757058","https://openalex.org/W3122907670","https://openalex.org/W3126217745","https://openalex.org/W3170547996","https://openalex.org/W3173380736","https://openalex.org/W3183671432","https://openalex.org/W3184890107","https://openalex.org/W3202721974","https://openalex.org/W3212156874","https://openalex.org/W4224912470","https://openalex.org/W4281889937","https://openalex.org/W4283163477","https://openalex.org/W4285246417","https://openalex.org/W4380569649","https://openalex.org/W4385245566","https://openalex.org/W4385570213","https://openalex.org/W4385572225","https://openalex.org/W4385574051","https://openalex.org/W4385574217","https://openalex.org/W4386566892","https://openalex.org/W4388483873","https://openalex.org/W6734194636","https://openalex.org/W6739901393","https://openalex.org/W6779277177"],"related_works":["https://openalex.org/W3049463507","https://openalex.org/W2936497627","https://openalex.org/W4288365749","https://openalex.org/W3013624417","https://openalex.org/W4287826556","https://openalex.org/W4287598411","https://openalex.org/W3098382480","https://openalex.org/W3198458223","https://openalex.org/W4288267738","https://openalex.org/W3126642501"],"abstract_inverted_index":{"The":[0,135,172],"advent":[1],"of":[2,58,96,110,122,141,158],"online":[3],"platforms":[4,39],"and":[5,15,29,86,115,177],"services":[6],"has":[7,21],"revolutionized":[8],"communication,":[9],"enabling":[10],"users":[11],"to":[12,42,45],"share":[13],"opinions":[14],"ideas":[16],"seamlessly.":[17],"However,":[18],"this":[19,146],"convenience":[20],"also":[22],"brought":[23],"about":[24],"a":[25,71],"surge":[26],"in":[27,64,79,179],"offensive":[28,47,66,76,102,123],"harmful":[30],"language":[31,81],"across":[32],"various":[33],"communication":[34],"mediums.":[35],"In":[36],"response,":[37],"social":[38],"have":[40],"turned":[41],"automated":[43],"methods":[44],"identify":[46],"content.":[48],"A":[49],"critical":[50],"research":[51],"question":[52],"emerges":[53],"when":[54],"investigating":[55],"the":[56,108,120,132,139,156],"role":[57],"specific":[59],"text":[60,77,103,124,170],"spans":[61,78],"within":[62],"comments":[63,82,99],"conveying":[65],"characteristics.":[67],"This":[68],"paper":[69],"conducted":[70],"comprehensive":[72],"investigation":[73],"into":[74],"detecting":[75],"Romanian":[80,98],"using":[83,165],"Transformer":[84],"encoders":[85],"Large":[87],"Language":[88],"Models":[89],"(LLMs).":[90],"We":[91,153],"introduced":[92],"an":[93],"extensive":[94],"dataset":[95],"4800":[97],"annotated":[100],"with":[101],"spans.":[104],"Moreover,":[105],"we":[106],"explored":[107],"impact":[109,157],"varying":[111],"model":[112],"sizes,":[113],"architectures,":[114],"training":[116],"data":[117],"volumes":[118],"on":[119,168],"performance":[121],"span":[125],"detection,":[126],"providing":[127],"valuable":[128],"insights":[129,176],"for":[130,138,145,162,182],"determining":[131],"optimal":[133],"configuration.":[134],"results":[136],"argue":[137],"effectiveness":[140],"BERT":[142],"pre-trained":[143],"models":[144],"span-detection":[147],"task,":[148],"showcasing":[149],"their":[150],"superior":[151],"performance.":[152],"further":[154],"investigated":[155],"different":[159],"sample-retrieval":[160],"strategies":[161],"few-shot":[163],"learning":[164],"LLMs":[166,181],"based":[167],"vector":[169],"representations.":[171],"analysis":[173],"highlights":[174],"important":[175],"trade-offs":[178],"leveraging":[180],"offensive-language-detection":[183],"tasks.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}