Modeling Annotator Perspective and Polarized Opinions to Improve Hate Speech Detection
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
In this paper we propose an approach to exploit the fine-grained knowledge expressed by individual human annotators during a hate speech (HS) detection task, before the aggregation of single judgments in a gold standard dataset eliminates non-majority perspectives. We automatically divide the annotators into groups, aiming at grouping them by similar personal characteristics (ethnicity, social background, culture etc.). To serve a multi-lingual perspective, we performed classification experiments on three different Twitter datasets in English and Italian languages. We created different gold standards, one for each group, and trained a state-of-the-art deep learning model on them, showing that supervised models informed by different perspectives on the target phenomena outperform a baseline represented by models trained on fully aggregated data. Finally, we implemented an ensemble approach that combines the single perspective-aware classifiers into an inclusive model. The results show that this strategy further improves the classification performance, especially with a significant boost in the recall of HS prediction.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
Deep Contextualized Word Representations
Peters, M., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1202 · Cited by 11,983
Universal Language Model Fine-tuning for Text Classification
Howard, J., & Ruder, S. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1031 · Cited by 4,100 · cited 2×
“(Howard and Ruder 2018) proposed the ULMFiT model for text classification tasks, achieving state-of-the-art performance on several benchmarks.”
MethodA 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 3×
“The majority of computational approaches to hate speech detection are based on supervised machine learning, including deep learning, but also Support Vector Machines, Random Forest, Logistic Regression and Decision Trees (Fortuna and Nunes 2018; Schmidt and Wiegand 2017).”
BackgroundMethod
Cited by
Feng, S., Park, C. Y., Liu, Y., & Tsvetkov, Y. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.656 · Cited by 149
Toward a Perspectivist Turn in Ground Truthing for Predictive Computing
Cabitza, F., Campagner, A., & Basile, V. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i6.25840 · Cited by 114
“…implications: first, supervised models equipped with full, non-aggregated annotations have been reported to exhibit a better prediction capability (Akhtar, Basile, and Patti 2020), in virtue of a better representation of the phenomena of interest; secondly, new techniques for AI explainability…”
BackgroundMethodInfluentialSelf-citationOffensive, aggressive, and hate speech analysis: From data-centric to human-centered approach
Kocoń, J., Figas, A., Gruza, M., Puchalska, D., Kajdanowicz, T., & Kazienko, P. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102643 · Cited by 103
Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation
Goyal, N., Kivlichan, I. D., Rosen, R., & Vasserman, L. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3555088 · Cited by 76
Combining FastText and Glove Word Embedding for Offensive and Hate speech Text Detection
Badri, N., Kboubi, F., & Chaibi, A. H. (2022) · Procedia Computer Science · doi:10.1016/j.procs.2022.09.132 · Cited by 65
The Ecological Fallacy in Annotation: Modeling Human Label Variation goes beyond Sociodemographics
Orlikowski, M., Röttger, P., Cimiano, P., & Hovy, D. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/2023.acl-short.88 · Cited by 9
Metadata
- Authors
- Akhtar, S., Basile, V., & Patti, V.
- Venue
- Proceedings of the AAAI Conference on Human Computation and Crowdsourcing
- Published
- 2020-10-01
- Volume
- 8
- Pages
- 151-154
- ISSN
- 2769-1330 (ISSN-L)
- 2769-1349
- OpenAlex
- W3092093993
- Cited by
- 50
- References
- 4
- FWCI
- 3.63
- Type
- conference paper
- Language
- en
- Open access
- diamond
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
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.