Using Sentiment Information for Preemptive Detection of Toxic Comments in Online Conversations
This work addresses the need for preemptive detection of toxicity in online platforms, but it is incremental as it builds on existing methods.
The paper tackled the problem of predicting toxic comments in online conversations by using sentiment information from initial messages, showing that adding sentiment features improves prediction accuracy.
The challenge of automatic detection of toxic comments online has been the subject of a lot of research recently, but the focus has been mostly on detecting it in individual messages after they have been posted. Some authors have tried to predict if a conversation will derail into toxicity using the features of the first few messages. In this paper, we combine that approach with previous work on toxicity detection using sentiment information, and show how the sentiments expressed in the first messages of a conversation can help predict upcoming toxicity. Our results show that adding sentiment features does help improve the accuracy of toxicity prediction, and also allow us to make important observations on the general task of preemptive toxicity detection.