You Are What You Tweet: Profiling Users by Past Tweets to Improve Hate Speech Detection
This work addresses the problem of improving hate speech detection for social media platforms by incorporating user-specific context, which is an incremental step in the field.
This paper explores the use of past tweets to profile users and improve hate speech detection. By augmenting three Twitter hate speech datasets with timeline data and embedding this context into a baseline model, the authors found promising results for better predicting hate speech.
Hate speech detection research has predominantly focused on purely content-based methods, without exploiting any additional context. We briefly critique pros and cons of this task formulation. We then investigate profiling users by their past utterances as an informative prior to better predict whether new utterances constitute hate speech. To evaluate this, we augment three Twitter hate speech datasets with additional timeline data, then embed this additional context into a strong baseline model. Promising results suggest merit for further investigation, though analysis is complicated by differences in annotation schemes and processes, as well as Twitter API limitations and data sharing policies.