{"id":"https://openalex.org/W7166139652","doi":"https://doi.org/10.29003/2075-7182-2026-24-438-447","title":"KazFakeCorpus: A bilingual multi-level corpus for semantic detection of fake news","display_name":"KazFakeCorpus: A bilingual multi-level corpus for semantic detection of fake news","publication_year":2026,"publication_date":"2026-06-19","ids":{"openalex":"https://openalex.org/W7166139652","doi":"https://doi.org/10.29003/2075-7182-2026-24-438-447"},"language":"en","primary_location":{"id":"doi:10.29003/2075-7182-2026-24-438-447","doi":"https://doi.org/10.29003/2075-7182-2026-24-438-447","is_oa":false,"landing_page_url":"https://doi.org/10.29003/2075-7182-2026-24-438-447","pdf_url":null,"source":{"id":"https://openalex.org/S4363606022","display_name":"Computational Linguistics and Intellectual Technologies","issn_l":"2075-7182","issn":["2075-7182"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["anvur-class-a","anvur-scientific","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics and Intellectual Technologies","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024743552","display_name":"Anargul Nekessova","orcid":"https://orcid.org/0009-0001-7642-0648","observed_orcids":["https://orcid.org/0009-0001-7642-0648"]},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Anargul Nekessova","raw_affiliation_strings":["L.N. Gumilyov Eurasian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L.N. Gumilyov Eurasian National University","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061479369","display_name":"\u0415\u043b\u0435\u043d\u0430 \u0421\u0438\u0434\u043e\u0440\u043e\u0432\u0430","orcid":"https://orcid.org/0000-0001-8731-3058","observed_orcids":["https://orcid.org/0000-0001-8731-3058"]},"institutions":[{"id":"https://openalex.org/I4387152644","display_name":"A.P. Ershov Institute of Informatics Systems, Siberian Branch of the Russian Academy of Sciences","ror":"https://ror.org/01dc8vg74","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210127387","https://openalex.org/I4387152644"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Elena Sidorova","raw_affiliation_strings":["A.P. Ershov Institute of Informatics Systems"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"A.P. Ershov Institute of Informatics Systems","institution_ids":["https://openalex.org/I4387152644"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071285401","display_name":"Zhanar Lamasheva","orcid":"https://orcid.org/0000-0002-9535-2636","observed_orcids":["https://orcid.org/0000-0002-9535-2636"]},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Zhanar Lamasheva","raw_affiliation_strings":["L.N. Gumilyov Eurasian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L.N. Gumilyov Eurasian National University","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135589855","display_name":"Madina Sambetbayeva","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Madina Sambetbayeva","raw_affiliation_strings":["L.N. Gumilyov Eurasian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L.N. Gumilyov Eurasian National University","institution_ids":["https://openalex.org/I10232997"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017370698","display_name":"Aigerim Yerimbetova","orcid":"https://orcid.org/0000-0002-2013-1513","observed_orcids":["https://orcid.org/0000-0002-2013-1513"]},"institutions":[{"id":"https://openalex.org/I4210135055","display_name":"Institute of Information and Computational Technologies","ror":"https://ror.org/03v6e0k54","country_code":"KZ","type":"facility","lineage":["https://openalex.org/I4210135055"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Aigerim Yerimbetova","raw_affiliation_strings":["Institute of Information and Computational Technologies CS MSHE RK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information and Computational Technologies CS MSHE RK","institution_ids":["https://openalex.org/I4210135055"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010098107","display_name":"Mira Kaldarova","orcid":"https://orcid.org/0000-0001-7494-9794","observed_orcids":["https://orcid.org/0000-0001-7494-9794"]},"institutions":[{"id":"https://openalex.org/I4403928190","display_name":"Astana International University","ror":"https://ror.org/0053vmf39","country_code":"KZ","type":"education","lineage":["https://openalex.org/I4403928190"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Mira Kaldarova","raw_affiliation_strings":["Higher School of Information Technology and Engineering, Astana International University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Higher School of Information Technology and Engineering, Astana International University","institution_ids":["https://openalex.org/I4403928190"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120126643","display_name":"Aksaule Nazymkhan","orcid":"https://orcid.org/0009-0007-4366-6709","observed_orcids":["https://orcid.org/0009-0007-4366-6709"]},"institutions":[{"id":"https://openalex.org/I10232997","display_name":"L. N. Gumilyov Eurasian National University","ror":"https://ror.org/0242cby63","country_code":"KZ","type":"education","lineage":["https://openalex.org/I10232997"]}],"countries":["KZ"],"is_corresponding":false,"raw_author_name":"Aksaule Nazymkhan","raw_affiliation_strings":["L.N. Gumilyov Eurasian National University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"L.N. Gumilyov Eurasian National University","institution_ids":["https://openalex.org/I10232997"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.42564103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"438","last_page":"447"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":1.0,"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/T11644","display_name":"Spam and Phishing Detection","score":0.0,"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"}},{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.0,"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/fake-news-detection","display_name":"fake news detection","score":0.9959999918937683},{"id":"https://openalex.org/keywords/disinformation","display_name":"disinformation","score":0.800000011920929},{"id":"https://openalex.org/keywords/message-reliability","display_name":"message reliability","score":0.7599999904632568},{"id":"https://openalex.org/keywords/misattribution","display_name":"misattribution","score":0.8309999704360962},{"id":"https://openalex.org/keywords/clickbait","display_name":"clickbait","score":0.9950000047683716},{"id":"https://openalex.org/keywords/emotional-pressure","display_name":"emotional pressure","score":0.6470000147819519},{"id":"https://openalex.org/keywords/synthetic-text-generation","display_name":"synthetic text generation","score":0.7390000224113464},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7839999794960022},{"id":"https://openalex.org/keywords/explainable-nlp","display_name":"explainable NLP","score":0.7540000081062317}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7633000016212463},{"id":"https://openalex.org/C2776552730","wikidata":"https://www.wikidata.org/wiki/Q189656","display_name":"Disinformation","level":3,"score":0.7008000016212463},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6746000051498413},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6445000171661377},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6190000176429749},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C2779756789","wikidata":"https://www.wikidata.org/wiki/Q28549308","display_name":"Fake news","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43799999356269836},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3522999882698059},{"id":"https://openalex.org/C2985727698","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Semantic annotation","level":3,"score":0.3319999873638153},{"id":"https://openalex.org/C2777946921","wikidata":"https://www.wikidata.org/wiki/Q7449044","display_name":"Semantic analysis (machine learning)","level":2,"score":0.32600000500679016},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C2781297163","wikidata":"https://www.wikidata.org/wiki/Q9252","display_name":"Kazakh","level":2,"score":0.28060001134872437},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.29003/2075-7182-2026-24-438-447","doi":"https://doi.org/10.29003/2075-7182-2026-24-438-447","is_oa":false,"landing_page_url":"https://doi.org/10.29003/2075-7182-2026-24-438-447","pdf_url":null,"source":{"id":"https://openalex.org/S4363606022","display_name":"Computational Linguistics and Intellectual Technologies","issn_l":"2075-7182","issn":["2075-7182"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["anvur-class-a","anvur-scientific","jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computational Linguistics and Intellectual Technologies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7163008155","https://openalex.org/W4413342587","https://openalex.org/W7221763679","https://openalex.org/W7139920353","https://openalex.org/W4415524300","https://openalex.org/W7165574952","https://openalex.org/W7167253416","https://openalex.org/W7162404681","https://openalex.org/W7167846182","https://openalex.org/W7169817916"],"abstract_inverted_index":{"The":[0,47,132],"paper":[1],"addresses":[2],"the":[3,15,56,64,71,123],"lack":[4],"of":[5,95,125],"bilingual":[6,24],"annotated":[7,26],"resources":[8],"for":[9,55,63,156],"automatic":[10],"fake":[11,36,136,153],"news":[12,137,154],"detection":[13,155],"in":[14,77,84,146],"KazakhRussian":[16],"media":[17],"space.":[18],"We":[19],"introduce":[20],"KazFakeCorpus,":[21],"a":[22,28,92,139],"balanced":[23],"corpus":[25,48],"using":[27],"multi-level":[29],"semantic":[30,141],"scheme":[31],"that":[32],"captures":[33],"message":[34],"reliability,":[35],"content":[37],"type,":[38],"disinformation":[39,147],"technique,":[40],"communicative":[41],"intent,":[42],"modality,":[43],"and":[44,59,69,79,104,128,143,151],"source":[45],"characteristics.":[46],"was":[49,82,98],"constructed":[50],"from":[51,113],"verified":[52],"Gov.kz":[53],"materials":[54],"REAL":[57],"class":[58],"synthetically":[60],"transformed":[61],"texts":[62,76,97],"FAKE":[65],"class.":[66],"After":[67],"preprocessing":[68],"balancing,":[70],"final":[72],"dataset":[73],"contains":[74],"4,276":[75],"Kazakh":[78],"Russian.":[80],"Annotation":[81],"performed":[83],"Label":[85],"Studio":[86],"by":[87],"two":[88],"independent":[89],"experts,":[90],"while":[91],"pilot":[93],"phase":[94],"120":[96],"used":[99],"to":[100,115],"refine":[101],"annotation":[102],"categories":[103],"guidelines.":[105],"Inter-annotator":[106],"agreement":[107],"measured":[108],"with":[109],"Krippendorff\u2019s":[110],"Alpha":[111],"ranged":[112],"0.79":[114],"0.88,":[116],"indicating":[117],"substantial":[118],"consistency.":[119],"Corpus":[120],"analysis":[121],"revealed":[122],"prevalence":[124],"misattribution,":[126],"clickbait,":[127],"emotional":[129],"pressure":[130],"techniques.":[131],"proposed":[133],"framework":[134],"models":[135],"as":[138],"structured":[140],"phenomenon":[142],"supports":[144],"research":[145],"analysis,":[148],"explainable":[149],"NLP,":[150],"cross-lingual":[152],"low-resource":[157],"languages.":[158]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-06-27T00:00:00"}
