Hate Speech Detection in Clubhouse

TL;DR

This paper introduces the first dataset for hate speech detection in voice chat rooms like Clubhouse, analyzing its characteristics and demonstrating that Perspective Scores outperform traditional text features in detection tasks.

Contribution

It presents the first dataset from Clubhouse for hate speech detection and evaluates high-level features like Perspective Scores for improved accuracy.

Findings

Perspective Scores outperform Bag of Words and Word2Vec

First dataset collection from Clubhouse for hate speech detection

Analysis of hate speech instances using statistical methods

Abstract

With the rise of voice chat rooms, a gigantic resource of data can be exposed to the research community for natural language processing tasks. Moderators in voice chat rooms actively monitor the discussions and remove the participants with offensive language. However, it makes the hate speech detection even more difficult since some participants try to find creative ways to articulate hate speech. This makes the hate speech detection challenging in new social media like Clubhouse. To the best of our knowledge all the hate speech datasets have been collected from text resources like Twitter. In this paper, we take the first step to collect a significant dataset from Clubhouse as the rising star in social media industry. We analyze the collected instances from statistical point of view using the Google Perspective Scores. Our experiments show that, the Perspective Scores can outperform Bag of Words and Word2Vec as high level text features.