{"url":"/task/abuse-detection","name":"Abuse Detection","slug":"abuse-detection","description_markdown":"Abuse detection is the task of identifying abusive behaviors, such as hate speech, offensive language, sexism and racism, in utterances from social media platforms (Source: https://arxiv.org/abs/1802.00385).","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":73,"papers_with_code":32,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":1,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/hate-speech-and-offensive-language","name":"Hate Speech and Offensive Language","full_name":"","num_papers_in_archive":67},{"url":"/dataset/wikiconv","name":"WikiConv","full_name":"","num_papers_in_archive":10},{"url":"/dataset/abuseanalyzer-dataset","name":"AbuseAnalyzer Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/coral-dataset","name":"CoRAL dataset","full_name":"CoRAL: a Context-aware Croatian Abusive Language Dataset","num_papers_in_archive":1}],"subtasks":[{"url":"/task/hate-speech-detection","name":"Hate Speech Detection"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":32,"tagged_in_all":73,"items":[{"url":"/paper/racial-bias-in-hate-speech-and-abusive","title":"Racial Bias in Hate Speech and Abusive Language Detection Datasets","date":"2019-05-29","arxiv_id":"1905.12516","repositories_listed":5,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/comparative-studies-of-detecting-abusive","title":"Comparative Studies of Detecting Abusive Language on Twitter","date":"2018-08-30","arxiv_id":"1808.10245","repositories_listed":4,"syntology":null},{"url":"/paper/hp-bert-a-framework-for-longitudinal-study-of","title":"HP-BERT: A framework for longitudinal study of Hinduphobia on social media via LLMs","date":"2025-01-07","arxiv_id":"2501.05482","repositories_listed":1,"syntology":null},{"url":"/paper/towards-cross-lingual-audio-abuse-detection","title":"Towards Cross-Lingual Audio Abuse Detection in Low-Resource Settings with Few-Shot Learning","date":"2024-12-02","arxiv_id":"2412.01408","repositories_listed":1,"syntology":null},{"url":"/paper/breaking-the-silence-detecting-and-mitigating","title":"Breaking the Silence Detecting and Mitigating Gendered Abuse in Hindi, Tamil, and Indian English Online Spaces","date":"2024-04-02","arxiv_id":"2404.02013","repositories_listed":1,"syntology":null},{"url":"/paper/tcab-a-large-scale-text-classification-attack","title":"TCAB: A Large-Scale Text Classification Attack Benchmark","date":"2022-10-21","arxiv_id":"2210.12233","repositories_listed":1,"syntology":null},{"url":"/paper/explainable-abuse-detection-as-intent","title":"Explainable Abuse Detection as Intent Classification and Slot Filling","date":"2022-10-06","arxiv_id":"2210.02659","repositories_listed":1,"syntology":null},{"url":"/paper/improving-generalizability-in-implicitly-1","title":"Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors","date":"2022-04-05","arxiv_id":"2204.02261","repositories_listed":1,"syntology":null},{"url":"/paper/entropy-based-attention-regularization-frees","title":"Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists","date":"2022-03-17","arxiv_id":"2203.09192","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/adima-abuse-detection-in-multilingual-audio","title":"ADIMA: Abuse Detection In Multilingual Audio","date":"2022-02-16","arxiv_id":"2202.07991","repositories_listed":1,"syntology":null},{"url":"/paper/convabuse-data-analysis-and-benchmarks-for","title":"ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI","date":"2021-09-20","arxiv_id":"2109.09483","repositories_listed":1,"syntology":null},{"url":"/paper/aaa-fair-evaluation-for-abuse-detection","title":"AAA: Fair Evaluation for Abuse Detection Systems Wanted","date":"2021-06-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/abuseanalyzer-abuse-detection-severity-and","title":"AbuseAnalyzer: Abuse Detection, Severity and Target Prediction for Gab Posts","date":"2020-09-30","arxiv_id":"2010.00038","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/kuisail-at-semeval-2020-task-12-bert-cnn-for","title":"KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Media","date":"2020-07-26","arxiv_id":"2007.13184","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/evaluating-performance-of-an-adult","title":"Evaluating Performance of an Adult Pornography Classifier for Child Sexual Abuse Detection","date":"2020-05-18","arxiv_id":"2005.08766","repositories_listed":1,"syntology":null},{"url":"/paper/intersectional-bias-in-hate-speech-and","title":"Intersectional Bias in Hate Speech and Abusive Language Datasets","date":"2020-05-12","arxiv_id":"2005.05921","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-meme-dataset-multioff-for","title":"Multimodal Meme Dataset (MultiOFF) for Identifying Offensive Content in Image and Text","date":"2020-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/kungfupanda-at-semeval-2020-task-12-bert","title":"Kungfupanda at SemEval-2020 Task 12: BERT-Based Multi-Task Learning for Offensive Language Detection","date":"2020-04-28","arxiv_id":"2004.13432","repositories_listed":1,"syntology":null},{"url":"/paper/wac-a-corpus-of-wikipedia-conversations-for","title":"WAC: A Corpus of Wikipedia Conversations for Online Abuse Detection","date":"2020-03-13","arxiv_id":"2003.06190","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/hatemonitors-language-agnostic-abuse","title":"HateMonitors: Language Agnostic Abuse Detection in Social Media","date":"2019-09-27","arxiv_id":"1909.12642","repositories_listed":1,"syntology":null},{"url":"/paper/multi-label-hate-speech-and-abusive-language","title":"Multi-label Hate Speech and Abusive Language Detection in Indonesian Twitter","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/pay-attention-to-your-context-when","title":"Pay ``Attention'' to your Context when Classifying Abusive Language","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/challenges-and-frontiers-in-abusive-content","title":"Challenges and frontiers in abusive content detection","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/online-abuse-detection-the-value-of","title":"Online abuse detection: the value of preprocessing and neural attention models","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/abusive-language-detection-in-online","title":"Abusive Language Detection in Online Conversations by Combining Content-and Graph-based Features","date":"2019-05-20","arxiv_id":"1905.07894","repositories_listed":1,"syntology":null},{"url":"/paper/um-iuling-at-semeval-2019-task-6-identifying","title":"UM-IU@LING at SemEval-2019 Task 6: Identifying Offensive Tweets Using BERT and SVMs","date":"2019-04-06","arxiv_id":"1904.03450","repositories_listed":1,"syntology":null},{"url":"/paper/transforma-at-semeval-2019-task-6-offensive","title":"Offensive Language Analysis using Deep Learning Architecture","date":"2019-03-12","arxiv_id":"1903.05280","repositories_listed":1,"syntology":null},{"url":"/paper/did-you-offend-me-classification-of-offensive","title":"Did you offend me? Classification of Offensive Tweets in Hinglish Language","date":"2018-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/author-profiling-for-abuse-detection","title":"Author Profiling for Abuse Detection","date":"2018-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/detecting-offensive-language-in-tweets-using","title":"Detecting Offensive Language in Tweets Using Deep Learning","date":"2018-01-13","arxiv_id":"1801.04433","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}