{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/racial-bias-in-hate-speech-and-abusive","title":"Racial Bias in Hate Speech and Abusive Language Detection Datasets","arxiv_id":"1905.12516","date":"2019-05-29","proceeding":"WS 2019 8","authors":["Thomas Davidson","Debasmita Bhattacharya","Ingmar Weber"],"abstract":"Technologies for abusive language detection are being developed and applied with little consideration of their potential biases. We examine racial bias in five different sets of Twitter data annotated for hate speech and abusive language. We train classifiers on these datasets and compare the predictions of these classifiers on tweets written in African-American English with those written in Standard American English. The results show evidence of systematic racial bias in all datasets, as classifiers trained on them tend to predict that tweets written in African-American English are abusive at substantially higher rates. If these abusive language detection systems are used in the field they will therefore have a disproportionate negative impact on African-American social media users. Consequently, these systems may discriminate against the groups who are often the targets of the abuse we are trying to detect.","url_abs":"https://arxiv.org/abs/1905.12516v1","url_pdf":"https://arxiv.org/pdf/1905.12516v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"racial-bias-in-hate-speech-and-abusive","repo_url":"https://github.com/LucilleN/dv-classifier","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"racial-bias-in-hate-speech-and-abusive","repo_url":"https://github.com/asking28/offenseval2020","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"racial-bias-in-hate-speech-and-abusive","repo_url":"https://github.com/asking28/sentimix2020","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"racial-bias-in-hate-speech-and-abusive","repo_url":"https://github.com/t-davidson/hate-speech-and-offensive-language","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"racial-bias-in-hate-speech-and-abusive","repo_url":"https://github.com/unitaryai/detoxify","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"abuse-detection","task_name":"Abuse Detection"},{"task_slug":"abusive-language","task_name":"Abusive Language"}],"methods":[{"method_slug":null,"method_name":"American"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1905.12516","atlas_url":"https://app.syntology.ai/?focus=1905.12516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.12516"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LucilleN/dv-classifier","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/t-davidson/hate-speech-and-offensive-language","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/asking28/sentimix2020","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/unitaryai/detoxify","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/asking28/offenseval2020","reach":{"status":"ok"}}],"summary":{"ran":4},"by_repo_kind":{"listed":{"samples":4,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f699c30e20a82f96","entry":"build_vocab","repo":"LucilleN/dv-classifier","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/LucilleN/dv-classifier/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f699c30e20a82f96"}},{"code_sha256_prefix":"c162df535f03de85","entry":"load_data","repo":"LucilleN/dv-classifier","repo_kind":"listed","path":"data_loader.py","file_url":"https://github.com/LucilleN/dv-classifier/blob/HEAD/data_loader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c162df535f03de85"}},{"code_sha256_prefix":"28e6e483d7fbbfac","entry":"reorder_minibatch","repo":"LucilleN/dv-classifier","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/LucilleN/dv-classifier/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"28e6e483d7fbbfac"}},{"code_sha256_prefix":"2d46d7a5d33366fd","entry":"strings_to_tensors","repo":"LucilleN/dv-classifier","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/LucilleN/dv-classifier/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2d46d7a5d33366fd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}