The opaque nature of deep learning models presents significant challenges for the ethical deployment of hate speech detection systems. To address this limitation, we introduce Supervised Rational Attention (SRA), a framework that explicitly aligns model attention with human rationales, improving both interpretability and fairness in hate speech classification. SRA integrates a supervised attention mechanism into transformer-based classifiers, optimizing a joint objective that combines standard classification loss with an alignment loss term that minimizes the discrepancy between attention weights and human-annotated rationales. We evaluated SRA on hate speech benchmarks in English (HateXplain) and Portuguese (HateBRXplain) with rationale annotations. Empirically, SRA achieves 2.4× better explainability compared to current baselines, and produces token-level explanations that are more faithful and human-aligned. In terms of fairness, SRA achieves competitive fairness across all measures, with second-best performance in detecting toxic posts targeting identity groups, while maintaining comparable results on other metrics. These findings demonstrate that incorporating human rationales into attention mechanisms can enhance interpretability and faithfulness without compromising fairness.

Nowadays, hate speech technologies are surely relevant in Brazil. Nevertheless, the inability of these technologies to provide reasons (rationales) for their decisions is the limiting factor to their adoption since they comprise bias, which may perpetuate social inequalities when propagated at scale. This scenario highlights the urgency of proposing explainable technologies to address hate speech. However, explainable models heavily depend on data availability with human-annotated rationales, which are scarce, especially for low-resource languages. To fill this relevant gap, we introduce HateBRXplain, the first benchmark dataset for hate speech detection in Portuguese, with text span annotations capturing rationales. We evaluated our corpus using mBERT, BERTimbau, DistilBERTimbau, and PTT5 models, which outperformed the current baselines. We further assessed these models’ explainability using model-agnostic explanation methods (LIME and SHAP). Results demonstrate plausible post-hoc explanations when compared to human annotations. However, the best-performing hate speech detection models failed to provide faithful rationales.

Due to the severity of the social media offensive and hateful comments in Brazil, and the lack of research in Portuguese, this paper provides the first large-scale expert annotated corpus of Brazilian Instagram comments for hate speech and offensive language detection. The HateBR corpus was collected from the comment section of Brazilian politicians’ accounts on Instagram and manually annotated by specialists, reaching a high inter-annotator agreement. The corpus consists of 7,000 documents annotated according to three different layers: a binary classification (offensive versus non-offensive comments), offensiveness-level classification (highly, moderately, and slightly offensive), and nine hate speech groups (xenophobia, racism, homophobia, sexism, religious intolerance, partyism, apology for the dictatorship, antisemitism, and fatphobia). We also implemented baseline experiments for offensive language and hate speech detection and compared them with a literature baseline. Results show that the baseline experiments on our corpus outperform the current state-of-the-art for the Portuguese language.

Most information is passed on in the form of language. Therefore, research on how people use language to inform and misinform, and how this knowledge may be automatically extracted from large amounts of text is surely relevant. This survey provides first-hand experiences and a comprehensive review of rhetorical-level structure analysis for online deception detection. We systematically analyze how discourse structure, aligned or not with other approaches, is applied to automatic fake news and fake reviews detection on the web and social media. Moreover, we categorize discourse-tagged corpora along with results, hence offering a summary and accessible introductions to new researchers.