Ex Machina: Personal Attacks Seen at Scale

Abstract

The damage personal attacks cause to online discourse motivates many platforms to try to curb the phenomenon. However, understanding the prevalence and impact of personal attacks in online platforms at scale remains surprisingly difficult. The contribution of this paper is to develop and illustrate a method that combines crowdsourcing and machine learning to analyze personal attacks at scale. We show an evaluation method for a classifier in terms of the aggregated number of crowd-workers it can approximate. We apply our methodology to English Wikipedia, generating a corpus of over 100k high quality human-labeled comments and 63M machine-labeled ones from a classifier that is as good as the aggregate of 3 crowd-workers, as measured by the area under the ROC curve and Spearman correlation. Using this corpus of machine-labeled scores, our methodology allows us to explore some of the open questions about the nature of online personal attacks. This reveals that the majority of personal attacks on Wikipedia are not the result of a few malicious users, nor primarily the consequence of allowing anonymous contributions from unregistered users.

References in corpus (1)

• A Web of Hate: Tackling Hateful Speech in Online Social Spaces

Cited by in corpus (15)

• Directions in Abusive Language Training Data: Garbage In, Garbage Out
• Community Interaction and Conflict on the Web
• The Structure of Toxic Conversations on Twitter
• Cyberbullying Detection in Social Networks Using Deep Learning Based Models; A Reproducibility Study
• Context-Aware Attention for Understanding Twitter Abuse
• Trajectories of Blocked Community Members: Redemption, Recidivism and Departure
• Detecting Online Hate Speech Using Context Aware Models
• Online Harassment in Majority Contexts: Examining Harms and Remedies across Countries
• Spillover of Antisocial Behavior from Fringe Platforms: The Unintended Consequences of Community Banning
• Thread With Caution: Proactively Helping Users Assess and Deescalate Tension in Their Online Discussions
• Automatically Detecting Cyberbullying Comments on Online Game Forums
• MetaHate: A Dataset for Unifying Efforts on Hate Speech Detection
• Understanding Multi-Turn Toxic Behaviors in Open-Domain Chatbots
• Adversarial Sampling for Fairness Testing in Deep Neural Network
• An Effective, Robust and Fairness-aware Hate Speech Detection Framework