# Toxicity Is a Property of Communicative Events: A Contextual Stress Measurement Framework for NLP

arXiv: https://arxiv.org/abs/2503.16072 · HTML: https://mlsanity.com/paper/2503.16072/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 79 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Builds on (most cited first, 12 of 12)

- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Annotators with Attitudes: How Annotator Beliefs And Identities Bias Toxic Language Detection](https://mlsanity.com/paper/2111.07997/) (2021)
- [Directions in Abusive Language Training Data: Garbage In, Garbage Out](https://mlsanity.com/paper/2004.01670/) (2020)
- [Toxicity Detection: Does Context Really Matter?](https://mlsanity.com/paper/2006.00998/) (2020)
- [Detecting Online Hate Speech Using Context Aware Models](https://mlsanity.com/paper/1710.07395/) (2017)
- [Is Your Toxicity My Toxicity? Exploring the Impact of Rater Identity on Toxicity Annotation](https://mlsanity.com/paper/2205.00501/) (2022)
- [Handling Bias in Toxic Speech Detection: A Survey](https://mlsanity.com/paper/2202.00126/) (2022)
- [Confronting Abusive Language Online: A Survey from the Ethical and Human Rights Perspective](https://mlsanity.com/paper/2012.12305/) (2020)
- [Abuse is Contextual, What about NLP? The Role of Context in Abusive Language Annotation and Detection](https://mlsanity.com/paper/2103.14916/) (2021)
- [The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification](https://mlsanity.com/paper/2105.02778/) (2021)
- [Hate Speech Criteria: A Modular Approach to Task-Specific Hate Speech Definitions](https://mlsanity.com/paper/2206.15455/) (2022)
- [The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs](https://mlsanity.com/paper/2501.18626/) (2025)

## Abstract (arXiv)

Toxicity detection has become core safety infrastructure for online moderation, dataset filtering, and deployed language-model systems. Yet most detectors still treat toxicity as an intrinsic property of isolated text. This position paper argues that toxicity detection should be evaluated as the contextual measurement of situated communicative harm, rather than as single-label text classification. Toxicity is not contained in words alone; it emerges when a communicative act is interpreted by an audience within a normative and social context. We introduce the Contextual Stress Framework (CSF), which defines toxicity as a relation between perceived norm violation and induced stress or disruption. CSF explains why text-intrinsic detectors overflag dialectal or reclaimed language, miss coded or pragmatic abuse, and remain brittle under meaning-preserving transformations.