Deep Learning for Hate Speech Detection in Tweets
This addresses the problem of automated hate speech detection for social media platforms and applications like content moderation, but it is incremental as it applies existing deep learning methods to a specific domain.
The paper tackled hate speech detection in tweets by classifying them as racist, sexist, or neither, and found that deep learning methods outperformed state-of-the-art char/word n-gram methods by approximately 18 F1 points on a benchmark dataset of 16K annotated tweets.
Hate speech detection on Twitter is critical for applications like controversial event extraction, building AI chatterbots, content recommendation, and sentiment analysis. We define this task as being able to classify a tweet as racist, sexist or neither. The complexity of the natural language constructs makes this task very challenging. We perform extensive experiments with multiple deep learning architectures to learn semantic word embeddings to handle this complexity. Our experiments on a benchmark dataset of 16K annotated tweets show that such deep learning methods outperform state-of-the-art char/word n-gram methods by ~18 F1 points.