{"id":"https://openalex.org/W3163571239","doi":"https://doi.org/10.3390/info12050205","title":"A Study of Multilingual Toxic Text Detection Approaches under Imbalanced Sample Distribution","display_name":"A Study of Multilingual Toxic Text Detection Approaches under Imbalanced Sample Distribution","publication_year":2021,"publication_date":"2021-05-12","ids":{"openalex":"https://openalex.org/W3163571239","doi":"https://doi.org/10.3390/info12050205","mag":"3163571239"},"language":"en","primary_location":{"id":"doi:10.3390/info12050205","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info12050205","pdf_url":"https://www.mdpi.com/2078-2489/12/5/205/pdf?version=1620809748","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/2078-2489/12/5/205/pdf?version=1620809748","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047455603","display_name":"Guizhe Song","orcid":"https://orcid.org/0000-0002-2588-7010"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guizhe Song","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China"],"raw_orcid":"https://orcid.org/0000-0002-2588-7010","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046871248","display_name":"Degen Huang","orcid":"https://orcid.org/0000-0002-8860-7805"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Degen Huang","raw_affiliation_strings":["School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037671044","display_name":"Zhifeng Xiao","orcid":"https://orcid.org/0000-0003-3327-8108"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhifeng Xiao","raw_affiliation_strings":["School of Engineering, Penn State Erie, The Behrend College, Erie, PA 16563, USA"],"raw_orcid":"https://orcid.org/0000-0003-3327-8108","affiliations":[{"raw_affiliation_string":"School of Engineering, Penn State Erie, The Behrend College, Erie, PA 16563, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5037671044"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.9108,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.88000059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"12","issue":"5","first_page":"205","last_page":"205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9993000030517578,"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":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.8149265050888062},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5938197374343872},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5510879755020142},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5146230459213257},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46459436416625977},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.4626722037792206},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4506330192089081},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4382878541946411},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4365631639957428},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4154939651489258},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4050108790397644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8149265050888062},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5938197374343872},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5510879755020142},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5146230459213257},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46459436416625977},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.4626722037792206},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4506330192089081},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4382878541946411},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4365631639957428},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4154939651489258},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4050108790397644},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info12050205","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info12050205","pdf_url":"https://www.mdpi.com/2078-2489/12/5/205/pdf?version=1620809748","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:5e511cb3d7e143e49a0aa65c6aa9a7b9","is_oa":true,"landing_page_url":"https://doaj.org/article/5e511cb3d7e143e49a0aa65c6aa9a7b9","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 12, Iss 5, p 205 (2021)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/12/5/205/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/info12050205","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"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":"Information; Volume 12; Issue 5; Pages: 205","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/info12050205","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info12050205","pdf_url":"https://www.mdpi.com/2078-2489/12/5/205/pdf?version=1620809748","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":0.8799999952316284,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3163571239.pdf"},"referenced_works_count":60,"referenced_works":["https://openalex.org/W80056832","https://openalex.org/W179875071","https://openalex.org/W1871142974","https://openalex.org/W1938755728","https://openalex.org/W2120615054","https://openalex.org/W2156580264","https://openalex.org/W2251421351","https://openalex.org/W2473555522","https://openalex.org/W2587282796","https://openalex.org/W2595653137","https://openalex.org/W2626778328","https://openalex.org/W2762484717","https://openalex.org/W2765906452","https://openalex.org/W2770073503","https://openalex.org/W2788625861","https://openalex.org/W2801887493","https://openalex.org/W2805705517","https://openalex.org/W2807229073","https://openalex.org/W2808423603","https://openalex.org/W2887128979","https://openalex.org/W2903822854","https://openalex.org/W2905232447","https://openalex.org/W2908694192","https://openalex.org/W2914120296","https://openalex.org/W2921834779","https://openalex.org/W2949300694","https://openalex.org/W2951559648","https://openalex.org/W2951737564","https://openalex.org/W2954992865","https://openalex.org/W2963532322","https://openalex.org/W2963626623","https://openalex.org/W2963748066","https://openalex.org/W2965849195","https://openalex.org/W2970269073","https://openalex.org/W2971150411","https://openalex.org/W2981478815","https://openalex.org/W2983040767","https://openalex.org/W2989817717","https://openalex.org/W2992016955","https://openalex.org/W3007065191","https://openalex.org/W3007706270","https://openalex.org/W3011385529","https://openalex.org/W3017367042","https://openalex.org/W3035390927","https://openalex.org/W3036262837","https://openalex.org/W3036891800","https://openalex.org/W3046087842","https://openalex.org/W3046283370","https://openalex.org/W3087144884","https://openalex.org/W3087484287","https://openalex.org/W3093198074","https://openalex.org/W3094547811","https://openalex.org/W3101319662","https://openalex.org/W3106169611","https://openalex.org/W3115906794","https://openalex.org/W3119860226","https://openalex.org/W3127924095","https://openalex.org/W3132303073","https://openalex.org/W3135855479","https://openalex.org/W3170547996"],"related_works":["https://openalex.org/W4386014872","https://openalex.org/W1847536016","https://openalex.org/W4361193986","https://openalex.org/W4378498597","https://openalex.org/W3101140821","https://openalex.org/W4287816966","https://openalex.org/W3015650676","https://openalex.org/W4389520445","https://openalex.org/W4387800341","https://openalex.org/W4388347706"],"abstract_inverted_index":{"Multilingual":[0,142],"characteristics,":[1],"lack":[2],"of":[3,55,175],"annotated":[4],"data,":[5],"and":[6,42,65,89,101,109,120,160,167,173],"imbalanced":[7],"sample":[8],"distribution":[9],"are":[10,92,137],"the":[11,47,77,113,129,133,140,150,155,171,176],"three":[12,125],"main":[13],"challenges":[14],"for":[15,76,94],"toxic":[16,28],"comment":[17],"analysis":[18],"in":[19,162],"a":[20,26,33,53,72],"multilingual":[21,27,82],"setting.":[22],"This":[23],"paper":[24],"proposes":[25],"text":[29,63],"classifier":[30],"which":[31,106],"adopts":[32],"novel":[34],"fusion":[35,126,152,178],"strategy":[36],"that":[37,149],"combines":[38],"different":[39],"loss":[40],"functions":[41],"multiple":[43],"pre-training":[44,95],"models.":[45,114],"Specifically,":[46],"proposed":[48,177],"learning":[49],"pipeline":[50],"starts":[51],"with":[52],"series":[54],"pre-processing":[56],"steps,":[57],"including":[58],"translation,":[59],"word":[60,69],"segmentation,":[61],"purification,":[62],"digitization,":[64],"vectorization,":[66],"to":[67,71,123],"convert":[68],"tokens":[70],"vectorized":[73],"form":[74],"suitable":[75],"downstream":[78],"tasks.":[79],"Two":[80],"models,":[81,158],"bidirectional":[83],"encoder":[84],"representation":[85],"from":[86],"transformers":[87],"(MBERT)":[88],"XLM-RoBERTa":[90],"(XLM-R),":[91],"employed":[93],"through":[96],"Masking":[97],"Language":[98,103],"Modeling":[99,104],"(MLM)":[100],"Translation":[102],"(TLM),":[105],"incorporate":[107],"semantic":[108],"contextual":[110],"information":[111],"into":[112],"We":[115],"train":[116],"six":[117],"base":[118],"models":[119,127,136],"fuse":[121],"them":[122],"obtain":[124],"using":[128],"F1":[130,163],"scores":[131],"as":[132],"weights.":[134],"The":[135],"evaluated":[138],"on":[139],"Jigsaw":[141],"Toxic":[143],"Comment":[144],"dataset.":[145],"Experimental":[146],"results":[147],"show":[148],"best":[151],"model":[153],"outperforms":[154],"two":[156],"state-of-the-art":[157],"MBERT":[159],"XLM-R,":[161],"score":[164],"by":[165],"5.05%":[166],"0.76%,":[168],"respectively,":[169],"verifying":[170],"effectiveness":[172],"robustness":[174],"strategy.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2021-05-24T00:00:00"}