EMNLP Findings2023
Unmasking the Hidden Meaning: Bridging Implicit and Explicit Hate Speech Embedding Representations
Nicolás Benjamín Ocampo, Elena Cabrio, Serena Villata
Abstract
Research on automatic hate speech (HS) detection has mainly focused on identifying explicit forms of hateful expressions on user-generated content. Recently, a few works have started to investigate methods to address more implicit and subtle abusive content. However, despite these efforts, automated systems still struggle to correctly recognize implicit and more veiled forms of HS. As these systems heavily rely on proper textual representations for classification, it is crucial to investigate the differences in embedding implicit and explicit messages. Our contribution to address this challenging task is fourfold. First, we present a comparative analysis of transformer-based models, evaluating their performance across five datasets containing implicit HS messages. Second, we examine the embedding representations of implicit messages across different targets, gaining insight into how veiled cases are encoded. Third, we compare and link explicit and implicit hateful messages across these datasets through their targets, enforcing the relation between explicitness and implicitness and obtaining more meaningful embedding representations. Lastly, we show how these newer representation maintains high performance on HS labels, while improving classification in borderline cases.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Causality Guided Representation Learning for Cross-Style Hate Speech Detection cites Latent Hatred: A Benchmark for Understanding Implicit Hate Speech
- Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation Vectors cites Social Bias Frames: Reasoning about Social and Power Implications of Language
- Latent Hatred: A Benchmark for Understanding Implicit Hate Speech cites Social Bias Frames: Reasoning about Social and Power Implications of Language
Cited by top-tier papers1
Builds on8
- What Makes for Good Views for Contrastive Learning?Yonglong Tian, Chen Sun, Ben Poole, Dilip Krishnan et al.NeurIPS 2020 · 1,631 citations
- Supervised Contrastive Learning for Pre-trained Language Model Fine-tuningBeliz Gunel, Jingfei Du, Alexis Conneau, Veselin StoyanovICLR 2021 · 595 citations
- Latent Hatred: A Benchmark for Understanding Implicit Hate SpeechMai ElSherief, Caleb Ziems, David Muchlinski, Vaishnavi Anupindi et al.EMNLP 2021 · 159 citations
- Improving Generalizability in Implicitly Abusive Language Detection with Concept Activation VectorsIsar Nejadgholi, Kathleen C. Fraser, Svetlana KiritchenkoACL 2022 · 27 citations
- Social Bias Frames: Reasoning about Social and Power Implications of LanguageMaarten Sap, Saadia Gabriel, Lianhui Qin, Dan Jurafsky et al.ACL 2020 · 16 citations
Related papers
- Playing the Part of the Sharp Bully: Generating Adversarial Examples for Implicit Hate Speech DetectionNicolás Benjamín Ocampo, Elena Cabrio, Serena VillataACL Findings 2023 · 15 citations
- AmpleHate: Amplifying the Attention for Versatile Implicit Hate DetectionYejin Lee, Joonghyuk Hahn, Hyeseon Ahn, Yo-Sub HanEMNLP 2025 · 2 citations
- Deciphering Implicit Hate: Evaluating Automated Detection Algorithms for Multimodal HateAustin Botelho, Scott Hale, Bertie VidgenACL Findings 2021 · 14 citations
- SharedCon: Implicit Hate Speech Detection using Shared SemanticsHyeseon Ahn, Youngwook Kim, Jungin Kim, Yo-Sub HanACL Findings 2024 · 13 citations
- Fight Fire with Fire: Fine-tuning Hate Detectors using Large Samples of Generated Hate SpeechTomer Wullach, Amir Adler, Einat MinkovEMNLP Findings 2021 · 33 citations
