{"id":"https://openalex.org/W2988713194","doi":"https://doi.org/10.26615/978-954-452-056-4_029","title":"Detecting Toxicity in News Articles: Application to Bulgarian","display_name":"Detecting Toxicity in News Articles: Application to Bulgarian","publication_year":2019,"publication_date":"2019-10-22","ids":{"openalex":"https://openalex.org/W2988713194","doi":"https://doi.org/10.26615/978-954-452-056-4_029","mag":"2988713194"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-056-4_029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.26615/978-954-452-056-4_029","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028121952","display_name":"Yoan Dinkov","orcid":"https://orcid.org/0009-0001-1415-8963"},"institutions":[{"id":"https://openalex.org/I58918642","display_name":"Sofia University \"St. Kliment Ohridski\"","ror":"https://ror.org/02jv3k292","country_code":"BG","type":"education","lineage":["https://openalex.org/I58918642"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Yoan Dinkov","raw_affiliation_strings":["Faculty of Mathematics and Informatics","Qatar Computing Research Institute HBKU Doha, Qatar","Sofia University Sofia, Bulgaria"],"affiliations":[{"raw_affiliation_string":"Sofia University Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]},{"raw_affiliation_string":"Faculty of Mathematics and Informatics","institution_ids":[]},{"raw_affiliation_string":"Qatar Computing Research Institute HBKU Doha, Qatar","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076908482","display_name":"Ivan Koychev","orcid":"https://orcid.org/0000-0003-3919-030X"},"institutions":[{"id":"https://openalex.org/I58918642","display_name":"Sofia University \"St. Kliment Ohridski\"","ror":"https://ror.org/02jv3k292","country_code":"BG","type":"education","lineage":["https://openalex.org/I58918642"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Ivan Koychev","raw_affiliation_strings":["Faculty of Mathematics and Informatics","Qatar Computing Research Institute HBKU Doha, Qatar","Sofia University Sofia, Bulgaria"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute HBKU Doha, Qatar","institution_ids":[]},{"raw_affiliation_string":"Sofia University Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]},{"raw_affiliation_string":"Faculty of Mathematics and Informatics","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012055259","display_name":"Preslav Nakov","orcid":"https://orcid.org/0000-0002-3600-1510"},"institutions":[{"id":"https://openalex.org/I58918642","display_name":"Sofia University \"St. Kliment Ohridski\"","ror":"https://ror.org/02jv3k292","country_code":"BG","type":"education","lineage":["https://openalex.org/I58918642"]}],"countries":["BG"],"is_corresponding":false,"raw_author_name":"Preslav Nakov","raw_affiliation_strings":["Faculty of Mathematics and Informatics","Qatar Computing Research Institute HBKU Doha, Qatar","Sofia University Sofia, Bulgaria"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute HBKU Doha, Qatar","institution_ids":[]},{"raw_affiliation_string":"Sofia University Sofia, Bulgaria","institution_ids":["https://openalex.org/I58918642"]},{"raw_affiliation_string":"Faculty of Mathematics and Informatics","institution_ids":[]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.726,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":12,"citation_normalized_percentile":{"value":0.635524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":88},"biblio":{"volume":null,"issue":null,"first_page":"247","last_page":"258"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9991,"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":0.9991,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.9991,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9847,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/bulgarian","display_name":"Bulgarian","score":0.8646791},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.78500324},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.5557531}],"concepts":[{"id":"https://openalex.org/C2780343019","wikidata":"https://www.wikidata.org/wiki/Q7918","display_name":"Bulgarian","level":2,"score":0.8646791},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.78500324},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7056165},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5978961},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.5557531},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49704483},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.47231814},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.44585913},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4423189},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.41680038},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35153908},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-056-4_029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1908.09785","pdf_url":"https://arxiv.org/pdf/1908.09785","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.26615/978-954-452-056-4_029","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":85,"referenced_works":["https://openalex.org/W1497523460","https://openalex.org/W1541280084","https://openalex.org/W2068138600","https://openalex.org/W2084591134","https://openalex.org/W2086456653","https://openalex.org/W2099813784","https://openalex.org/W2119432837","https://openalex.org/W2123329834","https://openalex.org/W2145451908","https://openalex.org/W2148143831","https://openalex.org/W2252009349","https://openalex.org/W232190577","https://openalex.org/W2338607651","https://openalex.org/W2407434113","https://openalex.org/W2512009388","https://openalex.org/W2513959045","https://openalex.org/W2538541058","https://openalex.org/W2542192908","https://openalex.org/W2548105042","https://openalex.org/W2577888896","https://openalex.org/W2588552579","https://openalex.org/W2593408211","https://openalex.org/W2594382603","https://openalex.org/W2604264634","https://openalex.org/W2607700676","https://openalex.org/W2735017898","https://openalex.org/W2736566371","https://openalex.org/W2742144412","https://openalex.org/W2742330194","https://openalex.org/W2749784378","https://openalex.org/W2756851436","https://openalex.org/W2759820691","https://openalex.org/W2768226620","https://openalex.org/W2772863019","https://openalex.org/W2788283367","https://openalex.org/W2790166049","https://openalex.org/W2791544114","https://openalex.org/W2792984539","https://openalex.org/W2794557536","https://openalex.org/W2798888217","https://openalex.org/W2803502351","https://openalex.org/W2808778018","https://openalex.org/W2845859134","https://openalex.org/W2869975551","https://openalex.org/W2887356313","https://openalex.org/W2888034114","https://openalex.org/W2889368497","https://openalex.org/W2890953671","https://openalex.org/W2896457183","https://openalex.org/W2914120296","https://openalex.org/W2929938180","https://openalex.org/W2931826965","https://openalex.org/W2946595845","https://openalex.org/W2949453732","https://openalex.org/W2949813784","https://openalex.org/W2950782805","https://openalex.org/W2952371036","https://openalex.org/W2952861497","https://openalex.org/W2954444514","https://openalex.org/W2962739339","https://openalex.org/W2962795929","https://openalex.org/W2963119657","https://openalex.org/W2963190210","https://openalex.org/W2963205619","https://openalex.org/W2963341956","https://openalex.org/W2963567867","https://openalex.org/W2963709474","https://openalex.org/W2963789354","https://openalex.org/W2963847405","https://openalex.org/W2963857245","https://openalex.org/W2963961878","https://openalex.org/W2963962958","https://openalex.org/W2963968475","https://openalex.org/W2965564330","https://openalex.org/W2966747465","https://openalex.org/W2970487286","https://openalex.org/W2971007730","https://openalex.org/W2971291998","https://openalex.org/W2972901607","https://openalex.org/W2978871345","https://openalex.org/W3204116757","https://openalex.org/W4288095223","https://openalex.org/W4289703743","https://openalex.org/W4297730508","https://openalex.org/W4301246714"],"related_works":["https://openalex.org/W4393207791","https://openalex.org/W4205697663","https://openalex.org/W2963159966","https://openalex.org/W2764165745","https://openalex.org/W2597038935","https://openalex.org/W2419357761","https://openalex.org/W2414976889","https://openalex.org/W2400831526","https://openalex.org/W1967857157","https://openalex.org/W1563422521"],"abstract_inverted_index":{"Online":[0],"media":[1,202,229,235],"aim":[2],"for":[3,9,67,128,181,270,315],"reaching":[4],"ever":[5,11],"bigger":[6],"audience":[7],"and":[8,23,30,34,94,105,132,148,195,217,237],"attracting":[10],"longer":[12],"attention":[13],"span.This":[14],"competition":[15],"creates":[16],"an":[17,144,267],"environment":[18],"that":[19,40,66,76,276,302,317],"rewards":[20],"sensational,":[21],"fake,":[22],"toxic":[24,46,93,212],"news.To":[25],"help":[26],"limit":[27],"their":[28],"spread":[29],"impact,":[31],"we":[32,55,84,123,133,173,177,280,303],"propose":[33],"develop":[35],"a":[36,59,64,86,111,125,139,149,179,208,211,312],"news":[37,74],"toxicity":[38,82,290],"detector":[39],"can":[41],"recognize":[42],"various":[43],"types":[44],"of":[45,113,120,146,152,189,198,266,306],"content.While":[47],"previous":[48,164],"research":[49,165],"primarily":[50],"focused":[51,167],"on":[52,102,170,185],"English,":[53,171],"here":[54,172],"target":[56,174],"Bulgarian.We":[57],"created":[58,124],"new":[60],"dataset":[61,180],"by":[62,284],"crawling":[63],"website":[65,259],"five":[68,206],"years":[69],"has":[70,166,193],"been":[71],"collecting":[72],"Bulgarian":[73,200],"articles":[75,240,316],"were":[77,250],"manually":[78],"categorized":[79],"into":[80,138],"eight":[81,92],"groups.Then":[83],"trained":[85],"multi-class":[87,286],"classifier":[88],"with":[89,98,110,245],"nine":[90],"categories:":[91],"one":[95],"non-toxic.We":[96],"experimented":[97],"different":[99],"representations":[100],"based":[101,184],"ElMo,":[103],"BERT,":[104],"XLM,":[106],"as":[107,109,220,222],"well":[108,221],"variety":[112],"domain-specific":[114],"features.Due":[115],"to":[116,234,262],"the":[117,159,186,199,204,218,223,256,264,289],"small":[118],"size":[119],"our":[121,182],"dataset,":[122],"separate":[126],"model":[127],"each":[129],"feature":[130],"type,":[131],"ultimately":[134],"combined":[135],"these":[136,307],"models":[137],"meta-classifier.The":[140],"evaluation":[141],"results":[142],"show":[143],"accuracy":[145],"59.0%":[147],"macro-F1":[150],"score":[151],"39.7%,":[153],"which":[154,192],"represent":[155,318],"sizable":[156],"improvements":[157],"over":[158,288],"majority-class":[160],"baseline":[161],"(Acc=30.3%,macro-F1=5.2%).While":[162],"most":[163],"almost":[168],"exclusively":[169],"Bulgarian.In":[175],"particular,":[176],"built":[178],"experiments":[183],"knowledge":[187],"base":[188],"Media":[190,257],"Scan,":[191],"catalogued":[194],"characterized":[196],"many":[197],"online":[201],"in":[203],"past":[205],"years.If":[207],"medium":[209],"published":[210],"news,":[213,293],"this":[214,282],"was":[215],"recorded":[216],"article,":[219],"medium,":[224],"got":[225],"labelled":[226,251],"accordingly.The":[227],"analyzed":[228],"vary":[230],"from":[231],"digital":[232],"newspapers,":[233],"groups":[236],"blogs.For":[238],"some":[239,254,273],"there":[241],"is":[242],"detailed":[243],"explanation":[244],"examples":[246],"about":[247,272],"why":[248],"they":[249],"like":[252],"that.In":[253],"cases,":[255],"Scan":[258],"describes":[260],"attempts":[261],"contact":[263],"authors":[265],"article":[268],"asking":[269],"clarification":[271],"questionable":[274],"facts":[275],"are":[277],"being":[278],"reported.Here":[279],"use":[281],"information":[283],"performing":[285],"classification":[287],"labels:":[291],"fake":[292],"sensations,":[294],"hate":[295],"speech,":[296],"conspiracies,":[297],"anti-democratic,":[298],"pro-authoritarian,":[299],"defamation,":[300],"delusion.Note":[301],"allow":[304],"multiple":[305],"labels":[308],"simultaneously.We":[309],"further":[310],"add":[311],"non-toxic":[313],"label":[314],"good":[319],"news.":[320]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2988713194","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5}],"updated_date":"2025-04-21T17:41:24.126453","created_date":"2019-11-22"}