{"id":"https://openalex.org/W7129084080","doi":"https://doi.org/10.1145/3773966.3777990","title":"From Data to Model in Bias: A Statistical Analysis of Political Bias in the C4 Corpus and Its Impact on LLMs","display_name":"From Data to Model in Bias: A Statistical Analysis of Political Bias in the C4 Corpus and Its Impact on LLMs","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129084080","doi":"https://doi.org/10.1145/3773966.3777990"},"language":null,"primary_location":{"id":"doi:10.1145/3773966.3777990","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777990","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773966.3777990","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050694256","display_name":"Jaebeom You","orcid":"https://orcid.org/0009-0003-9539-1875"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaebeom You","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University of Science and Technology, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0003-9539-1875","affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University of Science and Technology, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126072230","display_name":"Jaewon Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I110273157","display_name":"Kookmin University","ror":"https://ror.org/0049erg63","country_code":"KR","type":"education","lineage":["https://openalex.org/I110273157"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewon Lee","raw_affiliation_strings":["Department of AI, Big Data & Management, Kookmin University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0009-7104-8208","affiliations":[{"raw_affiliation_string":"Department of AI, Big Data & Management, Kookmin University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I110273157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146732396","display_name":"Sehun Lee","orcid":"https://orcid.org/0009-0009-2234-190X"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sehun Lee","raw_affiliation_strings":["Department of Economics, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0009-2234-190X","affiliations":[{"raw_affiliation_string":"Department of Economics, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126156580","display_name":"Hyuk-Yoon Kwon","orcid":null},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyuk-Yoon Kwon","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University of Science and Technology, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1125-6533","affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University of Science and Technology, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I118373667"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":58.4706,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.99798387,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"860","last_page":"870"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.34540000557899475,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.34540000557899475,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"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/T13629","display_name":"Text Readability and Simplification","score":0.12549999356269836,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.0697999969124794,"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/politics","display_name":"Politics","score":0.519599974155426},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.5178999900817871},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.38019999861717224},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.2736000120639801}],"concepts":[{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.519599974155426},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.5178999900817871},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.46369999647140503},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.3433000147342682},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3384000062942505},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.2987000048160553},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.29679998755455017},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.26739999651908875},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773966.3777990","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777990","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3773966.3777990","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773966.3777990","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Nineteenth ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2037698344","https://openalex.org/W2110065044","https://openalex.org/W2888161220","https://openalex.org/W2963416784","https://openalex.org/W2970200208","https://openalex.org/W3035241006","https://openalex.org/W3035591180","https://openalex.org/W3133702157","https://openalex.org/W3134354193","https://openalex.org/W3177468621","https://openalex.org/W3198599617","https://openalex.org/W3213241618","https://openalex.org/W4206292552","https://openalex.org/W4206590911","https://openalex.org/W4385564993","https://openalex.org/W4390738750","https://openalex.org/W4399322156","https://openalex.org/W4401170130","https://openalex.org/W4401955911","https://openalex.org/W4403681535","https://openalex.org/W4404132421","https://openalex.org/W4412944273","https://openalex.org/W4412945607"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2026-02-17T00:00:00"}