The Social World of Content Abusers in Community Question Answering

TL;DR

This paper analyzes user behavior in community question answering platforms, revealing that flag counts alone are insufficient to identify abuse, and introduces a network-based classifier achieving high accuracy in detecting abusive users.

Contribution

It uncovers the limitations of flag-based moderation and proposes a network property-based method to improve abuse detection in Q&A communities.

Findings

Flag counts do not fully identify abusive users.

Abusive users exhibit homophilous network behavior.

The classifier achieves up to 83% accuracy in detection.

Abstract

Community-based question answering platforms can be rich sources of information on a variety of specialized topics, from finance to cooking. The usefulness of such platforms depends heavily on user contributions (questions and answers), but also on respecting the community rules. As a crowd-sourced service, such platforms rely on their users for monitoring and flagging content that violates community rules. Common wisdom is to eliminate the users who receive many flags. Our analysis of a year of traces from a mature Q&A site shows that the number of flags does not tell the full story: on one hand, users with many flags may still contribute positively to the community. On the other hand, users who never get flagged are found to violate community rules and get their accounts suspended. This analysis, however, also shows that abusive users are betrayed by their network properties: we find strong evidence of homophilous behavior and use this finding to detect abusive users who go under the community radar. Based on our empirical observations, we build a classifier that is able to detect abusive users with an accuracy as high as 83%.