Hate Speech Detection is Not as Easy as You May Think: A Closer Look at Model Validation
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Hate speech is an important problem that is seriously affecting the dynamics and usefulness of online social communities. Large scale social platforms are currently investing important resources into automatically detecting and classifying hateful content, without much success. On the other hand, the results reported by state-of-the-art systems indicate that supervised approaches achieve almost perfect performance but only within specific datasets. In this work, we analyze this apparent contradiction between existing literature and actual applications. We study closely the experimental methodology used in prior work and their generalizability to other datasets. Our findings evidence methodological issues, as well as an important dataset bias. As a consequence, performance claims of the current state-of-the-art have become significantly overestimated. The problems that we have found are mostly related to data overfitting and sampling issues. We discuss the implications for current research and re-conduct experiments to give a more accurate picture of the current state-of-the art methods.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Bag of Tricks for Efficient Text Classification
Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers · doi:10.18653/v1/e17-2068 · Cited by 4,545
Bag of Tricks for Efficient Text Classification
Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2016) · arXiv · doi:10.48550/arxiv.1607.01759 · Cited by 4,542
Automated Hate Speech Detection and the Problem of Offensive Language
Davidson, T., Warmsley, D., Macy, M., & Weber, I. (2017) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v11i1.14955 · Cited by 2,610
A Survey on Automatic Detection of Hate Speech in Text
Fortuna, P., & Nunes, S. (2019) · ACM Computing Surveys · doi:10.1145/3232676 · Cited by 1,241 · cited 5×
“It is used in several hate-speech detection studies [1, 2, 6, 13, 18, 23, 32] and it is consistently mentioned as an important source in the surveys about the subject [11, 26, 27].”
BackgroundMethodInfluentialEx Machina: Personal Attacks Seen at Scale
Wulczyn, E., Thain, N., & Dixon, L. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052591 · Cited by 636
Deep Learning for Detecting Cyberbullying Across Multiple Social Media Platforms
Agrawal, S., & Awekar, A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-76941-7_11 · Cited by 387 · cited 10×
“More recently, Deep Learning methods have attracted interest to hate-speech detection [1, 2, 13, 18, 23, 32].”
BackgroundMethodResultInfluentialApproaches to automated detection of cyberbullying: A survey
Salawu, S., He, Y., & Lumsden, J. (2020) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2017.2761757 · Cited by 258 · cited 3×
“Automatic detection of hate speech has become an increasingly relevant research topic in the past few years [11, 26, 27].”
BackgroundDetection of Cyberbullying Incidents on the Instagram Social Network
Hosseinmardi, H., Mattson, S. A., Rafiq, R. I., Han, R., Lv, Q., & Mishra, S. (2015) · arXiv · doi:10.48550/arxiv.1503.03909 · Cited by 126
Cyberbullying Detection in Social Networks Using Deep Learning Based Models; A Reproducibility Study
Dadvar, M., & Eckert, K. (2018) · arXiv · doi:10.48550/arxiv.1812.08046 · Cited by 71
Cited by
HateXplain: A Benchmark Dataset for Explainable Hate Speech Detection
Mathew, B., Saha, P., Yimam, S. M., Biemann, C., Goyal, P., & Mukherjee, A. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i17.17745 · Cited by 513
Choi, M., Pei, J., Kumar, S., Shu, C., & Jurgens, D. (2023) · arXiv · doi:10.48550/arxiv.2305.14938 · Cited by 73
Cyberbullying Detection in Social Networks Using Bi-GRU with Self-Attention Mechanism
Fang, Y., Yang, S., Zhao, B., & Huang, C. (2021) · Information · doi:10.3390/info12040171 · Cited by 74
“However, two noteworthy studies [30,31] discussed the limitations of the above”
BackgroundHate speech detection: A comprehensive review of recent works
Gandhi, A., Ahir, P., Adhvaryu, K., Shah, P., Lohiya, R., Cambria, E., Poria, S., & Hussain, A. (2024) · Expert Systems · doi:10.1111/exsy.13562 · Cited by 66
SoK: Content Moderation in Social Media, from Guidelines to Enforcement, and Research to Practice
Singhal, M., Ling, C., Paudel, P., Thota, P., Kumarswamy, N., Stringhini, G., & Nilizadeh, S. (2023) · 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P) · doi:10.1109/eurosp57164.2023.00056 · Cited by 57
Metadata
- Authors
- Arango, A., Pérez, J., & Poblete, B.
- Venue
- Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval
- Publisher
- ACM
- Published
- 2019-07-18
- Pages
- 45-54
- OpenAlex
- W2954479967
- Cited by
- 153
- References
- 10
- FWCI
- 8.51
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Hate Speech Detection is Not as Easy as You May Think: A Closer Look at Model Validation. https://app.cochat.ai/papers/10.1145/3331184.3331262
- The paper
- Arango, A., Pérez, J., & Poblete, B. (2019). Hate Speech Detection is Not as Easy as You May Think: A Closer Look at Model Validation. Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. https://doi.org/10.1145/3331184.3331262
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.