{"id":"https://openalex.org/W4412526091","doi":"https://doi.org/10.3390/bdcc9070190","title":"Detection of Biased Phrases in the Wiki Neutrality Corpus for Fairer Digital Content Management Using Artificial Intelligence","display_name":"Detection of Biased Phrases in the Wiki Neutrality Corpus for Fairer Digital Content Management Using Artificial Intelligence","publication_year":2025,"publication_date":"2025-07-21","ids":{"openalex":"https://openalex.org/W4412526091","doi":"https://doi.org/10.3390/bdcc9070190"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc9070190","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9070190","pdf_url":"https://www.mdpi.com/2504-2289/9/7/190/pdf?version=1753102429","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"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":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/9/7/190/pdf?version=1753102429","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099518063","display_name":"Abdullah Abdullah","orcid":"https://orcid.org/0000-0002-7983-2189"},"institutions":[{"id":"https://openalex.org/I59225215","display_name":"Bahria University","ror":"https://ror.org/02v8d7770","country_code":"PK","type":"education","lineage":["https://openalex.org/I59225215"]},{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX","PK"],"is_corresponding":false,"raw_author_name":"Abdullah","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional, Mexico City 07738, Mexico","Department of Computer Science, Bahria University Lahore Campus, Lahore 54600, Pakistan"],"affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional, Mexico City 07738, Mexico","institution_ids":["https://openalex.org/I59361560"]},{"raw_affiliation_string":"Department of Computer Science, Bahria University Lahore Campus, Lahore 54600, Pakistan","institution_ids":["https://openalex.org/I59225215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110663173","display_name":"Muhammad Ateeb Ather","orcid":"https://orcid.org/0009-0004-5397-6768"},"institutions":[{"id":"https://openalex.org/I59225215","display_name":"Bahria University","ror":"https://ror.org/02v8d7770","country_code":"PK","type":"education","lineage":["https://openalex.org/I59225215"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Ateeb Ather","raw_affiliation_strings":["Department of Computer Science, Bahria University Lahore Campus, Lahore 54600, Pakistan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Bahria University Lahore Campus, Lahore 54600, Pakistan","institution_ids":["https://openalex.org/I59225215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061018630","display_name":"Olga Kolesnikova","orcid":"https://orcid.org/0000-0002-1307-1647"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Olga Kolesnikova","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional, Mexico City 07738, Mexico"],"affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional, Mexico City 07738, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008287867","display_name":"Grigori Sidorov","orcid":"https://orcid.org/0000-0003-3901-3522"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"Grigori Sidorov","raw_affiliation_strings":["Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional, Mexico City 07738, Mexico"],"affiliations":[{"raw_affiliation_string":"Centro de Investigaci\u00f3n en Computaci\u00f3n, Instituto Polit\u00e9cnico Nacional, Mexico City 07738, Mexico","institution_ids":["https://openalex.org/I59361560"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008287867"],"corresponding_institution_ids":["https://openalex.org/I59361560"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":8.3566,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.97260368,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"9","issue":"7","first_page":"190","last_page":"190"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9277999997138977,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9277999997138977,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.920199990272522,"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":0.569962739944458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5613740086555481},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5419017672538757},{"id":"https://openalex.org/keywords/neutrality","display_name":"Neutrality","score":0.5268306136131287},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5264742374420166},{"id":"https://openalex.org/keywords/digital-content","display_name":"Digital content","score":0.44205451011657715},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32589733600616455},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.26636064052581787},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12216439843177795},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.09968206286430359}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.569962739944458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5613740086555481},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5419017672538757},{"id":"https://openalex.org/C2779581858","wikidata":"https://www.wikidata.org/wiki/Q9049677","display_name":"Neutrality","level":2,"score":0.5268306136131287},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5264742374420166},{"id":"https://openalex.org/C2779344036","wikidata":"https://www.wikidata.org/wiki/Q11320476","display_name":"Digital content","level":2,"score":0.44205451011657715},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32589733600616455},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.26636064052581787},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12216439843177795},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.09968206286430359},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/bdcc9070190","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9070190","pdf_url":"https://www.mdpi.com/2504-2289/9/7/190/pdf?version=1753102429","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"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":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4ab7ba6177aa47b08d1a1497c5cd4a2d","is_oa":true,"landing_page_url":"https://doaj.org/article/4ab7ba6177aa47b08d1a1497c5cd4a2d","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Big Data and Cognitive Computing, Vol 9, Iss 7, p 190 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/bdcc9070190","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9070190","pdf_url":"https://www.mdpi.com/2504-2289/9/7/190/pdf?version=1753102429","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"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":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412526091.pdf","grobid_xml":"https://content.openalex.org/works/W4412526091.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W2898227265","https://openalex.org/W3033129824","https://openalex.org/W3111112601","https://openalex.org/W3166773976","https://openalex.org/W3172871932","https://openalex.org/W4386783354","https://openalex.org/W4402671265","https://openalex.org/W4402671454","https://openalex.org/W4403718012","https://openalex.org/W4406444846","https://openalex.org/W4406924314","https://openalex.org/W4408309490","https://openalex.org/W4408472883","https://openalex.org/W4410466881","https://openalex.org/W4411630291","https://openalex.org/W4412376900","https://openalex.org/W4412499637","https://openalex.org/W6745609711","https://openalex.org/W6778883912","https://openalex.org/W6864116162","https://openalex.org/W7010490795"],"related_works":["https://openalex.org/W2472237388","https://openalex.org/W4211168656","https://openalex.org/W2572059069","https://openalex.org/W2547660074","https://openalex.org/W4241049928","https://openalex.org/W2336273751","https://openalex.org/W4401545295","https://openalex.org/W4404547058","https://openalex.org/W2901136370","https://openalex.org/W4406744868"],"abstract_inverted_index":{"Detecting":[0],"biased":[1,39],"language":[2],"in":[3,17],"large-scale":[4],"corpora,":[5],"such":[6,64,137],"as":[7,65,138],"the":[8,36,115,164],"Wiki":[9],"Neutrality":[10],"Corpus,":[11],"is":[12,86],"essential":[13],"for":[14,35,171],"promoting":[15],"neutrality":[16],"digital":[18],"content.":[19],"This":[20],"study":[21],"systematically":[22],"evaluates":[23],"a":[24,94,128],"range":[25],"of":[26,38,131,166],"machine":[27],"learning":[28,32,169],"(ML)":[29],"and":[30,40,54,77,91,107,141,153,158,176,180],"deep":[31,168],"(DL)":[33],"models":[34,170],"detection":[37],"pre-conditioned":[41],"phrases.":[42],"Conventional":[43],"classifiers,":[44],"including":[45],"Extreme":[46],"Gradient":[47],"Boosting":[48,56],"(XGBoost),":[49],"Light":[50],"Gradient-Boosting":[51],"Machine":[52],"(LightGBM),":[53],"Categorical":[55],"(CatBoost),":[57],"are":[58],"compared":[59],"with":[60,99],"advanced":[61],"neural":[62],"architectures":[63],"Bidirectional":[66],"Encoder":[67],"Representations":[68],"from":[69],"Transformers":[70],"(BERT),":[71],"Long":[72],"Short-Term":[73],"Memory":[74],"(LSTM)":[75],"networks,":[76],"Generative":[78],"Adversarial":[79],"Networks":[80],"(GANs).":[81],"A":[82],"novel":[83],"hybrid":[84,125,167],"architecture":[85],"proposed,":[87],"integrating":[88],"DistilBERT,":[89],"LSTM,":[90],"GANs":[92],"within":[93],"unified":[95],"framework.":[96],"Extensive":[97],"experimentation":[98],"intermediate":[100],"variants":[101],"DistilBERT":[102,108],"+":[103,109],"LSTM":[104],"(without":[105,111],"GAN)":[106],"GAN":[110],"LSTM)":[112],"demonstrates":[113],"that":[114],"fully":[116],"integrated":[117],"model":[118,126],"consistently":[119],"outperforms":[120],"all":[121],"alternatives.":[122],"The":[123,161],"proposed":[124],"achieves":[127],"cross-validation":[129],"accuracy":[130],"99.00%,":[132],"significantly":[133],"surpassing":[134],"traditional":[135],"baselines":[136],"XGBoost":[139],"(96.73%)":[140],"LightGBM":[142],"(96.83%).":[143],"It":[144],"also":[145],"exhibits":[146],"superior":[147],"stability,":[148],"statistical":[149],"significance":[150],"(paired":[151],"t-tests),":[152],"favorable":[154],"trade-offs":[155],"between":[156],"performance":[157],"computational":[159],"efficiency.":[160],"results":[162],"underscore":[163],"potential":[165],"capturing":[172],"subtle":[173],"linguistic":[174],"bias":[175],"advancing":[177],"more":[178],"objective":[179],"reliable":[181],"automated":[182],"content":[183],"moderation":[184],"systems.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}