Ex Machina: Personal Attacks Seen at Scale

TL;DR

This paper presents a scalable method combining crowdsourcing and machine learning to analyze personal attacks on online platforms, applied to Wikipedia, revealing attack patterns and challenging common assumptions.

Contribution

It introduces a novel evaluation approach for classifiers using crowd-worker aggregation and applies it to large-scale Wikipedia comment analysis.

Findings

Most attacks are not from a few malicious users

Attacks are not mainly due to anonymous contributions

The methodology enables large-scale attack analysis

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.