Characterizing (Un)moderated Textual Data in Social Systems

TL;DR

This study compares moderated Twitter and unmoderated Gab social media platforms, revealing that unmoderated content exhibits more negative sentiment, toxicity, and hate speech, informing hate speech detection efforts.

Contribution

The paper provides a comparative analysis of linguistic and toxic features in moderated versus unmoderated social media content, highlighting differences relevant to hate speech detection.

Findings

Unmoderated Gab content shows more negative sentiment.

Unmoderated content has higher toxicity levels.

Unmoderated environments contain proportionally more hate speech.

Abstract

Despite the valuable social interactions that online media promote, these systems provide space for speech that would be potentially detrimental to different groups of people. The moderation of content imposed by many social media has motivated the emergence of a new social system for free speech named Gab, which lacks moderation of content. This article characterizes and compares moderated textual data from Twitter with a set of unmoderated data from Gab. In particular, we analyze distinguishing characteristics of moderated and unmoderated content in terms of linguistic features, evaluate hate speech and its different forms in both environments. Our work shows that unmoderated content presents different psycholinguistic features, more negative sentiment and higher toxicity. Our findings support that unmoderated environments may have proportionally more online hate speech. We hope our analysis and findings contribute to the debate about hate speech and benefit systems aiming at deploying hate speech detection approaches.