--- title: "Automated Hate Speech Detection and the — Davidson 2017" description: "The paper addresses a weakness in automatic hate speech detection: systems often fail to tell genuine hate speech apart from merely offensive language…" authors: ["Thomas Davidson", "Dana Warmsley", "Michael Macy", "Ingmar Weber"] year: 2017 venue: "arXiv:1703.04009" source: "https://arxiv.org/abs/1703.04009" doi: "10.48550/arxiv.1703.04009" arxiv: "1703.04009" licence: "arXiv — non-exclusive license to distribute" licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/davidson-2017-automated-hate-speech-detection-problem/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/davidson-2017-automated-hate-speech-detection-problem/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/) / Automated Hate Speech Detection and the Problem of Offensive Language # Automated Hate Speech Detection and the Problem of Offensive Language **Authors:** [Thomas Davidson](https://md.research.elamur.ai/free/en/authors/thomas-davidson/), [Dana Warmsley](https://md.research.elamur.ai/free/en/authors/dana-warmsley/), Michael Macy, [Ingmar Weber](https://md.research.elamur.ai/free/en/authors/ingmar-weber/) · **Year:** 2017 · **Venue:** arXiv:1703.04009 · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/) **Links:** [Publisher's page](https://arxiv.org/abs/1703.04009) · [PDF](https://arxiv.org/pdf/1703.04009) · [DOI 10.48550/arxiv.1703.04009](https://doi.org/10.48550/arxiv.1703.04009) · [arXiv 1703.04009](https://arxiv.org/abs/1703.04009) · [OpenAlex](https://openalex.org/W2951737564) **Citations:** 263 citations (openalex-snapshot · 2026-10-14) · [744](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary The paper addresses a weakness in automatic hate speech detection: systems often fail to tell genuine hate speech apart from merely offensive language, such as casual slurs, profanity, or quoted rap lyrics. Keyword-based approaches therefore produce many false positives. The authors used the Hatebase.org lexicon to collect tweets, gathered user timelines, and had a sample annotated by CrowdFlower workers. Each tweet was assigned one of three classes: hate speech, offensive only, or neither. They then trained a one-versus-rest logistic regression with L2 regularization. Its features included TF-IDF word n-grams, POS n-grams, readability scores, sentiment, and tweet metadata. Overall scores were high, but the hate class remained difficult, and errors leaned toward predicting milder categories. The error analysis found that racist and homophobic content is more readily treated as hate, while sexist content tends to be judged only offensive. Hate speech without explicit slurs was hard to catch. The work matters because merging the two categories inflates hate speech prevalence and wrongly labels many users as hate speakers. ## Key points - **Data:** Lexicon searches identified 33,458 Twitter users, whose timelines yielded 85.4M tweets. From these, 25k lexicon-matching tweets were sampled and labeled by at least three CrowdFlower coders each, with 92% agreement. Majority voting produced 24,802 labeled tweets. - **Class distribution:** Only about 5% of tweets were majority-labeled as hate speech, and just 1.3% unanimously. Roughly 76% were labeled offensive and 16.6% neither, which shows the low precision of the Hatebase lexicon. - **Method:** Tweets were preprocessed with the Porter stemmer, and POS tags came from NLTK. Logistic regression with L1 regularization was used for feature reduction. A grid search compared naive Bayes, decision trees, random forests, linear SVM, and logistic regression, all implemented in scikit-learn. - **Results:** Overall precision was 0.91, recall 0.90, and F1 0.90. For the hate class, however, precision was only 0.44 and recall 0.61, so about 40% of hate tweets were misclassified. Conversely, around 5% of offensive tweets and 2% of neutral tweets were wrongly labeled as hate. - **Resource and lexical insights:** The authors released a smaller, higher-precision version of the Hatebase lexicon on GitHub (t-davidson/hate-speech-and-offensive-language). Their analysis showed that some terms (e.g., "n*gger", "f*ggot") strongly signal hate, while their variants (e.g., "n*gga", "f*g") occur in both hate speech and ordinary offensive usage. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Other](https://md.research.elamur.ai/free/en/shelves/other/) ## Cited by Cited by 744 papers of our library cite it (of the 140673 whose bibliographies we read); 54 of them have a page here, 690 not yet. - [From Linguistics to Practice: a Case Study of Offensive Language Taxonomy in Hebrew](https://md.research.elamur.ai/free/en/papers/aclbulk-2024-liebeskind-linguistics-practice-case-study-offensive/) - [Propaganda to Hate: A Multimodal Analysis of Arabic Memes with Multi-Agent LLMs](https://md.research.elamur.ai/free/en/papers/alam-2024-propaganda-hate-multimodal-analysis-arabic/) - [Multi-task Learning with Active Learning for Arabic Offensive Speech Detection](https://md.research.elamur.ai/free/en/papers/alansari-2025-multi-task-learning-active-learning/) - [ArMIS - The Arabic Misogyny and Sexism Corpus with Annotator Subjective Disagreements](https://md.research.elamur.ai/free/en/papers/almanea-2022-armis-arabic-misogyny-sexism-corpus/) - [Hurtlex: A Multilingual Lexicon of Words to Hurt](https://md.research.elamur.ai/free/en/papers/bassignana-2018-hurtlex-multilingual-lexicon-words-hurt/) - [Overview of the EVALITA 2018 Hate Speech Detection Task](https://md.research.elamur.ai/free/en/papers/bosco-2018-overview-evalita-2018-hate-speech/) - [A Multi-Platform Arabic News Comment Dataset for Offensive Language Detection](https://md.research.elamur.ai/free/en/papers/chowdhury-2020-multi-platform-arabic-news-comment/) - [CONAN - COunter NArratives through Nichesourcing: a Multilingual Dataset of Responses to Fight Online Hate Speech](https://md.research.elamur.ai/free/en/papers/chung-2019-conan-counter-narratives-through-nichesourcing/) - [A Corpus of Turkish Offensive Language on Social Media](https://md.research.elamur.ai/free/en/papers/coltekin-2020-corpus-turkish-offensive-language-social/) - [Racial Bias in Hate Speech and Abusive Language Detection Datasets](https://md.research.elamur.ai/free/en/papers/davidson-2019-racial-bias-hate-speech-abusive/) - [Build it Break it Fix it for Dialogue Safety: Robustness from Adversarial Human Attack](https://md.research.elamur.ai/free/en/papers/dinan-2019-build-it-break-it-fix/) - [Latent Hatred: A Benchmark for Understanding Implicit Hate Speech](https://md.research.elamur.ai/free/en/papers/elsherief-2021-latent-hatred-benchmark-understanding-implicit/) - [Toxic, Hateful, Offensive or Abusive? What Are We Really Classifying? An Empirical Analysis of Hate Speech Datasets](https://md.research.elamur.ai/free/en/papers/fortuna-2020-toxic-hateful-offensive-or-abusive/) - [A Multi-Task Benchmark for Abusive Language Detection in Low-Resource Settings](https://md.research.elamur.ai/free/en/papers/gaim-2025-multi-task-benchmark-abusive-language/) - [Using Convolutional Neural Networks to Classify Hate-Speech](https://md.research.elamur.ai/free/en/papers/gamback-2017-convolutional-neural-networks-classify-hate/) - [Hate Towards the Political Opponent: A Twitter Corpus Study of the 2020 US Elections on the Basis of Offensive Speech and Stance Detection](https://md.research.elamur.ai/free/en/papers/grimminger-2021-hate-political-opponent-twitter-corpus/) - [Sexism detection: The first corpus in Algerian dialect with a code-switching in Arabic/ French and English](https://md.research.elamur.ai/free/en/papers/guellil-2021-sexism-detection-first-corpus-algerian/) - [ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection](https://md.research.elamur.ai/free/en/papers/hartvigsen-2022-toxigen-large-scale-machine-generated/) - [Arabic Offensive Language Detection Using Machine Learning and Ensemble Machine Learning Approaches](https://md.research.elamur.ai/free/en/papers/husain-2020-arabic-offensive-language-detection-using/) - [Contextualizing Hate Speech Classifiers with Post-hoc Explanation](https://md.research.elamur.ai/free/en/papers/kennedy-2020-contextualizing-hate-speech-classifiers-post/) - [The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes](https://md.research.elamur.ai/free/en/papers/kiela-2020-hateful-memes-challenge-detecting-hate/) - [Benchmarking Aggression Identification in Social Media](https://md.research.elamur.ai/free/en/papers/kumar-2018-benchmarking-aggression-identification-social-media/) - [Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement](https://md.research.elamur.ai/free/en/papers/leonardelli-2021-agreeing-disagree-annotating-offensive-language/) - [CultureLLM: Incorporating Cultural Differences into Large Language Models](https://md.research.elamur.ai/free/en/papers/li-2024-culturellm-incorporating-cultural-differences-large/) - [Offensive language detection in Hebrew: can other languages help?](https://md.research.elamur.ai/free/en/papers/lingbulk-2022-litvak-offensive-language-detection-hebrew-can/) - [NULI at SemEval-2019 Task 6: Transfer Learning for Offensive Language Detection using Bidirectional Transformers](https://md.research.elamur.ai/free/en/papers/liu-2019-nuli-semeval-2019-task-6/) - [Detecting Anti-Semitic Hate Speech using Transformer-based Large Language Models](https://md.research.elamur.ai/free/en/papers/liu-2024-detecting-anti-semitic-hate-speech/) - [A Holistic Approach to Undesired Content Detection in the Real World](https://md.research.elamur.ai/free/en/papers/markov-2022-holistic-approach-undesired-content-detection/) - [Arabic Offensive Language on Twitter: Analysis and Experiments](https://md.research.elamur.ai/free/en/papers/mubarak-2021-arabic-offensive-language-twitter-analysis/) - [Automatic Expansion and Retargeting of Arabic Offensive Language Training](https://md.research.elamur.ai/free/en/papers/mubarak-2021-automatic-expansion-retargeting-arabic-offensive/) - [Emojis as Anchors to Detect Arabic Offensive Language and Hate Speech](https://md.research.elamur.ai/free/en/papers/mubarak-2022-emojis-anchors-detect-arabic-offensive/) - [Multilingual and Multi-Aspect Hate Speech Analysis](https://md.research.elamur.ai/free/en/papers/ousidhoum-2019-multilingual-multi-aspect-hate-speech/) - [Toxicity Detection: Does Context Really Matter?](https://md.research.elamur.ai/free/en/papers/pavlopoulos-2020-toxicity-detection-does-context-really/) - [Can LLMs Evaluate What They Cannot Annotate? Revisiting LLM Reliability in Hate Speech Detection](https://md.research.elamur.ai/free/en/papers/piot-2026-can-llms-evaluate-what-they/) - [Offensive Language Identification in Greek](https://md.research.elamur.ai/free/en/papers/pitenis-2020-offensive-language-identification-greek/) - [A Benchmark Dataset for Learning to Intervene in Online Hate Speech](https://md.research.elamur.ai/free/en/papers/qian-2019-benchmark-dataset-learning-intervene-online/) - [Explainable AI for Ethical Counter Speech Generation in Hate Speech Mitigation](https://md.research.elamur.ai/free/en/papers/ridoy-2026-explainable-ai-ethical-counter-speech/) - [Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks](https://md.research.elamur.ai/free/en/papers/rottger-2022-two-contrasting-data-annotation-paradigms/) - [KUISAIL at SemEval-2020 Task 12: BERT-CNN for Offensive Speech Identification in Social Media](https://md.research.elamur.ai/free/en/papers/safaya-2020-kuisail-semeval-2020-task-12/) - [Fighting Offensive Language on Social Media with Unsupervised Text Style Transfer](https://md.research.elamur.ai/free/en/papers/santos-2018-fighting-offensive-language-social-media/) - [The Risk of Racial Bias in Hate Speech Detection](https://md.research.elamur.ai/free/en/papers/sap-2019-risk-racial-bias-hate-speech/) - [Social Bias Frames: Reasoning about Social and Power Implications of Language](https://md.research.elamur.ai/free/en/papers/sap-2020-social-bias-frames-reasoning-about/) - [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://md.research.elamur.ai/free/en/papers/sap-2022-annotators-attitudes-how-annotator-beliefs/) - [Large Language Model Alignment: A Survey](https://md.research.elamur.ai/free/en/papers/shen-2023-large-language-model-alignment-survey/) - [mGPT: Few-Shot Learners Go Multilingual](https://md.research.elamur.ai/free/en/papers/shliazhko-2022-mgpt-few-shot-learners-go/) - [Offensive Language and Hate Speech Detection for Danish](https://md.research.elamur.ai/free/en/papers/sigurbergsson-2020-offensive-language-hate-speech-detection/) - [Challenges and frontiers in abusive content detection](https://md.research.elamur.ai/free/en/papers/vidgen-2019-challenges-frontiers-abusive-content-detection/) - [Learning from the Worst: Dynamically Generated Datasets to Improve Online Hate Detection](https://md.research.elamur.ai/free/en/papers/vidgen-2021-learning-worst-dynamically-generated-datasets/) - [Challenges in Detoxifying Language Models](https://md.research.elamur.ai/free/en/papers/welbl-2021-challenges-detoxifying-language-models/) - [Predicting the Type and Target of Offensive Posts in Social Media](https://md.research.elamur.ai/free/en/papers/zampieri-2019-predicting-type-target-offensive-posts/) - [SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)](https://md.research.elamur.ai/free/en/papers/zampieri-2019-semeval-2019-task-6-identifying/) - [Conversations Gone Awry: Detecting Early Signs of Conversational Failure](https://md.research.elamur.ai/free/en/papers/zhang-2018-conversations-gone-awry-detecting-early/) - [Challenges in Automated Debiasing for Toxic Language Detection](https://md.research.elamur.ai/free/en/papers/zhou-2021-challenges-automated-debiasing-toxic-language/) - [VALUE: Understanding Dialect Disparity in NLU](https://md.research.elamur.ai/free/en/papers/ziems-2022-value-understanding-dialect-disparity-nlu/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{davidson2017automated, title = {{Automated Hate Speech Detection and the Problem of Offensive Language}}, author = {Davidson, Thomas and Warmsley, Dana and Macy, Michael and Weber, Ingmar}, year = {2017}, doi = {10.48550/arxiv.1703.04009}, eprint = {1703.04009}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.1703.04009} } ``` - [← previous Attention-based Recurrent Convolutional Neural Network for Automatic Essay Scoring](https://md.research.elamur.ai/free/en/papers/dong-2017-attention-based-recurrent-convolutional-neural/) - [next → Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction](https://md.research.elamur.ai/free/en/papers/bryant-2017-automatic-annotation-evaluation-error-types/) - [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/) ## References 15 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Bird, S.; Loper, E.; and Klein, E. 2009. Natural Language Processing with Python. O’Reilly Media Inc. [find](https://scholar.google.com/scholar?q=Bird%2C+S%2E%3B+Loper%2C+E%2E%3B+and+Klein%2C+E%2E+2009%2E+Natural+Language+Processing+with+Python%2E+O%E2%80%99Reilly+Media+Inc%2E) 2. Burnap, P., and Williams, M. L. 2015. Cyber hate speech on twitter: An application of machine classification and statistical modeling for policy and decision making. Policy & Internet 7(2):223– 242. [find](https://scholar.google.com/scholar?q=Burnap%2C+P%2E%2C+and+Williams%2C+M%2E+L%2E+2015%2E+Cyber+hate+speech+on+twitter%3A+An+application+of+machine+classification+and+statistical+modeling+for+policy+and+decision+making%2E+Policy+%26+Internet+7%282%29%3A223%E2%80%93+242%2E) 3. Djuric, N.; Zhou, J.; Morris, R.; Grbovic, M.; Radosavljevic, V.; and Bhamidipati, N. 2015. Hate speech detection with comment embeddings. In WWW, 29–30. [find](https://scholar.google.com/scholar?q=Djuric%2C+N%2E%3B+Zhou%2C+J%2E%3B+Morris%2C+R%2E%3B+Grbovic%2C+M%2E%3B+Radosavljevic%2C+V%2E%3B+and+Bhamidipati%2C+N%2E+2015%2E+Hate+speech+detection+with+comment+embeddings%2E+In+WWW%2C+29%E2%80%9330%2E) 4. Gitari, N. D.; Zuping, Z.; Damien, H.; and Long, J. 2015. A lexicon-based approach for hate speech detection. International Journal of Multimedia and Ubiquitous Engineering 10:215–230. [find](https://scholar.google.com/scholar?q=Gitari%2C+N%2E+D%2E%3B+Zuping%2C+Z%2E%3B+Damien%2C+H%2E%3B+and+Long%2C+J%2E+2015%2E+A+lexicon%2Dbased+approach+for+hate+speech+detection%2E+International+Journal+of+Multimedia+and+Ubiquitous+Engineering+10%3A215%E2%80%93230%2E) 5. Hutto, C. J., and Gilbert, E. 2014. VADER: A parsimonious rule-based model for sentiment analysis of social media text. In ICWSM. [find](https://scholar.google.com/scholar?q=Hutto%2C+C%2E+J%2E%2C+and+Gilbert%2C+E%2E+2014%2E+VADER%3A+A+parsimonious+rule%2Dbased+model+for+sentiment+analysis+of+social+media+text%2E+In+ICWSM%2E) 6. Jacobs, J. B., and Potter, K. 2000. Hate crimes: Criminal Law and Identity Politics. Oxford University Press. [find](https://scholar.google.com/scholar?q=Jacobs%2C+J%2E+B%2E%2C+and+Potter%2C+K%2E+2000%2E+Hate+crimes%3A+Criminal+Law+and+Identity+Politics%2E+Oxford+University+Press%2E) 7. Kwok, I., and Wang, Y. 2013. Locate the hate: Detecting tweets against blacks. In AAAI. [find](https://scholar.google.com/scholar?q=Kwok%2C+I%2E%2C+and+Wang%2C+Y%2E+2013%2E+Locate+the+hate%3A+Detecting+tweets+against+blacks%2E+In+AAAI%2E) 8. Nobata, C.; Tetreault, J.; Thomas, A.; Mehdad, Y.; and Chang, Y. 2016. Abusive language detection in online user content. In WWW, 145–153. [find](https://scholar.google.com/scholar?q=Nobata%2C+C%2E%3B+Tetreault%2C+J%2E%3B+Thomas%2C+A%2E%3B+Mehdad%2C+Y%2E%3B+and+Chang%2C+Y%2E+2016%2E+Abusive+language+detection+in+online+user+content%2E+In+WWW%2C+145%E2%80%93153%2E) 9. Pedregosa, F., et al. 2011. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research 12:2825–2830. [find](https://scholar.google.com/scholar?q=Pedregosa%2C+F%2E%2C+et+al%2E+2011%2E+Scikit%2Dlearn%3A+Machine+learning+in+Python%2E+Journal+of+Machine+Learning+Research+12%3A2825%E2%80%932830%2E) 10. Silva, L. A.; Mondal, M.; Correa, D.; Benevenuto, F.; and Weber, I. 2016. Analyzing the targets of hate in online social media. In ICWSM, 687–690. [find](https://scholar.google.com/scholar?q=Silva%2C+L%2E+A%2E%3B+Mondal%2C+M%2E%3B+Correa%2C+D%2E%3B+Benevenuto%2C+F%2E%3B+and+Weber%2C+I%2E+2016%2E+Analyzing+the+targets+of+hate+in+online+social+media%2E+In+ICWSM%2C+687%E2%80%93690%2E) 11. Walker, S. 1994. Hate Speech: The History of an American Controversy. U of Nebraska Press. [find](https://scholar.google.com/scholar?q=Walker%2C+S%2E+1994%2E+Hate+Speech%3A+The+History+of+an+American+Controversy%2E+U+of+Nebraska+Press%2E) 12. Wang, W.; Chen, L.; Thirunarayan, K.; and Sheth, A. P. 2014. Cursing in english on twitter. In CSCW, 415–425. [find](https://scholar.google.com/scholar?q=Wang%2C+W%2E%3B+Chen%2C+L%2E%3B+Thirunarayan%2C+K%2E%3B+and+Sheth%2C+A%2E+P%2E+2014%2E+Cursing+in+english+on+twitter%2E+In+CSCW%2C+415%E2%80%93425%2E) 13. Warner, W., and Hirschberg, J. 2012. Detecting hate speech on the world wide web. In LSM, 19–26. [find](https://scholar.google.com/scholar?q=Warner%2C+W%2E%2C+and+Hirschberg%2C+J%2E+2012%2E+Detecting+hate+speech+on+the+world+wide+web%2E+In+LSM%2C+19%E2%80%9326%2E) [our card](https://md.research.elamur.ai/free/en/papers/warner-2012-detecting-hate-speech-world-wide/) 14. Waseem, Z., and Hovy, D. 2016. Hateful symbols or hateful people? predictive features for hate speech detection on twitter. In SRW@HLT-NAACL, 88–93. [find](https://scholar.google.com/scholar?q=Waseem%2C+Z%2E%2C+and+Hovy%2C+D%2E+2016%2E+Hateful+symbols+or+hateful+people%3F+predictive+features+for+hate+speech+detection+on+twitter%2E+In+SRW%40HLT%2DNAACL%2C+88%E2%80%9393%2E) [our card](https://md.research.elamur.ai/free/en/papers/waseem-2016-hateful-symbols-or-hateful-people/) 15. Waseem, Z. 2016. Are you a racist or am i seeing things? annotator influence on hate speech detection on twitter. In Proceedings of the First Workshop on NLP and CSS, 138–142. [find](https://scholar.google.com/scholar?q=Waseem%2C+Z%2E+2016%2E+Are+you+a+racist+or+am+i+seeing+things%3F+annotator+influence+on+hate+speech+detection+on+twitter%2E+In+Proceedings+of+the+First+Workshop+on+NLP+and+CSS%2C+138%E2%80%93142%2E) [our card](https://md.research.elamur.ai/free/en/papers/waseem-2016-are-you-racist-or-am/)