# Abuse is Contextual, What about NLP? The Role of Context in Abusive Language Annotation and Detection

arXiv: https://arxiv.org/abs/2103.14916 · HTML: https://mlsanity.com/paper/2103.14916/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 46 references that are in the map.
- First posted on arXiv 27 Mar 2021.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Learning Word Vectors for 157 Languages](https://mlsanity.com/paper/1802.06893/) (2018)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)](https://mlsanity.com/paper/1903.08983/) (2019)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [Toxicity Detection: Does Context Really Matter?](https://mlsanity.com/paper/2006.00998/) (2020)
- [Conversations Gone Awry: Detecting Early Signs of Conversational Failure](https://mlsanity.com/paper/1805.05345/) (2018)
- [Detecting Online Hate Speech Using Context Aware Models](https://mlsanity.com/paper/1710.07395/) (2017)
- [A Just and Comprehensive Strategy for Using NLP to Address Online Abuse](https://mlsanity.com/paper/1906.01738/) (2019)
- [One-step and Two-step Classification for Abusive Language Detection on Twitter](https://mlsanity.com/paper/1706.01206/) (2017)
- [Disembodied Machine Learning: On the Illusion of Objectivity in NLP](https://mlsanity.com/paper/2101.11974/) (2021)
- [Mean Birds: Detecting Aggression and Bullying on Twitter](https://mlsanity.com/paper/1702.06877/) (2017)
- [Quantifying Intimacy in Language](https://mlsanity.com/paper/2011.03020/) (2020)
- [Something's Brewing! Early Prediction of Controversy-causing Posts from Discussion Features](https://mlsanity.com/paper/1904.07372/) (2019)
- [You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP](https://mlsanity.com/paper/1909.00412/) (2019)
- [Predictive Embeddings for Hate Speech Detection on Twitter](https://mlsanity.com/paper/1809.10644/) (2018)
- [Examining a hate speech corpus for hate speech detection and popularity prediction](https://mlsanity.com/paper/1805.04661/) (2018)
- [Comparative Studies of Detecting Abusive Language on Twitter](https://mlsanity.com/paper/1808.10245/) (2018)

## Built on by (most cited first, 19 of 19)

- [Safeguarding Large Language Models: A Survey](https://mlsanity.com/paper/2406.02622/) (2024)
- [On the Safety of Conversational Models: Taxonomy, Dataset, and Benchmark](https://mlsanity.com/paper/2110.08466/) (2021)
- [Do LLMs Understand Social Knowledge? Evaluating the Sociability of Large Language Models with SocKET Benchmark](https://mlsanity.com/paper/2305.14938/) (2023)
- [ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI](https://mlsanity.com/paper/2109.09483/) (2021)
- [Hate Speech and Counter Speech Detection: Conversational Context Does Matter](https://mlsanity.com/paper/2206.06423/) (2022)
- [From Dogwhistles to Bullhorns: Unveiling Coded Rhetoric with Language Models](https://mlsanity.com/paper/2305.17174/) (2023)
- [Revisiting Contextual Toxicity Detection in Conversations](https://mlsanity.com/paper/2111.12447/) (2021)
- [Toxicity Detection can be Sensitive to the Conversational Context](https://mlsanity.com/paper/2111.10223/) (2021)
- [Your spouse needs professional help: Determining the Contextual Appropriateness of Messages through Modeling Social Relationships](https://mlsanity.com/paper/2307.02763/) (2023)
- [CRUSH: Contextually Regularized and User anchored Self-supervised Hate speech Detection](https://mlsanity.com/paper/2204.06389/) (2022)
- [A Taxonomy of Rater Disagreements: Surveying Challenges & Opportunities from the Perspective of Annotating Online Toxicity](https://mlsanity.com/paper/2311.04345/) (2023)
- [Analyzing Norm Violations in Live-Stream Chat](https://mlsanity.com/paper/2305.10731/) (2023)
- [Putting Context in Context: the Impact of Discussion Structure on Text Classification](https://mlsanity.com/paper/2402.02975/) (2024)
- [On the definition of toxicity in NLP](https://mlsanity.com/paper/2310.02357/) (2023)
- [Graphically Speaking: Unmasking Abuse in Social Media with Conversation Insights](https://mlsanity.com/paper/2504.01902/) (2025)
- [Context Misleads LLMs: The Role of Context Filtering in Maintaining Safe Alignment of LLMs](https://mlsanity.com/paper/2508.10031/) (2025)
- [The Unappreciated Role of Intent in Algorithmic Moderation of Social Media Content](https://mlsanity.com/paper/2405.11030/) (2024)
- [Toxicity Is a Property of Communicative Events: A Contextual Stress Measurement Framework for NLP](https://mlsanity.com/paper/2503.16072/) (2025)
- [Leveraging LLMs for Context-Aware Implicit Textual and Multimodal Hate Speech Detection](https://mlsanity.com/paper/2510.15685/) (2025)

## Abstract (arXiv)

The datasets most widely used for abusive language detection contain lists of messages, usually tweets, that have been manually judged as abusive or not by one or more annotators, with the annotation performed at message level. In this paper, we investigate what happens when the hateful content of a message is judged also based on the context, given that messages are often ambiguous and need to be interpreted in the context of occurrence. We first re-annotate part of a widely used dataset for abusive language detection in English in two conditions, i.e. with and without context. Then, we compare the performance of three classification algorithms obtained on these two types of dataset, arguing that a context-aware classification is more challenging but also more similar to a real application scenario.