Revisiting Contextual Toxicity Detection in Conversations
Authors:
- Atijit AnuchitanukulAAAtijit Anuchitanukul
- Julia IveJIJulia Ive
- Lucia SpeciaLSLucia Specia
Preprint
Abstract
Understanding toxicity in user conversations is undoubtedly an important problem. Addressing "covert" or implicit cases of toxicity is particularly hard and requires context. Very few previous studies have analysed the influence of conversational context in human perception or in automated detection models. We dive deeper into both these directions. We start by analysing existing contextual datasets and come to the conclusion that toxicity labelling by humans is in general influenced by the conversational structure, polarity and topic of the context. We then propose to bring these findings into computational detection models by introducing and evaluating (a) neural architectures for contextual toxicity detection that are aware of the conversational structure, and (b) data augmentation strategies that can help model contextual toxicity detection. Our results have shown the encouraging potential of neural architectures that are aware of the conversation structure. We have also demonstrated that such models can benefit from synthetic data, especially in the social media domain.Keywords
All Related Versions
This publication has 24 references indexed in Scilit:
- Text Data Augmentation for Deep LearningJournal of Big Data, 2021
- On the Dangers of Stochastic Parrots2021
- Array programming with NumPyNature, 2020
- Generation and evaluation of artificial mental health records for Natural Language Processingnpj Digital Medicine, 2020
- Exploring Hate Speech Detection in Multimodal Publications2020
- Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation2020
- Toxicity Detection: Does Context Really Matter?2020
- The Second Conversational Intelligence Challenge (ConvAI2)2019
- Measuring and Mitigating Unintended Bias in Text Classification2018
- Large Scale Crowdsourcing and Characterization of Twitter Abusive BehaviorProceedings of the International AAAI Conference on Web and Social Media, 2018