Detecting Sockpuppetry on Wikipedia Using Meta-Learning

TL;DR

This paper introduces a meta-learning approach to detect sockpuppets on Wikipedia, improving adaptability and precision in identifying malicious accounts even with limited data, and provides a new dataset for future research.

Contribution

It applies meta-learning to sockpuppet detection, enabling rapid adaptation to new sockpuppet groups and surpassing previous models in prediction accuracy.

Findings

Meta-learning improves detection precision over traditional models.

The approach adapts quickly to new sockpuppet behaviours.

A new dataset for sockpuppet investigation is released.

Abstract

Malicious sockpuppet detection on Wikipedia is critical to preserving access to reliable information on the internet and preventing the spread of disinformation. Prior machine learning approaches rely on stylistic and meta-data features, but do not prioritise adaptability to author-specific behaviours. As a result, they struggle to effectively model the behaviour of specific sockpuppet-groups, especially when text data is limited. To address this, we propose the application of meta-learning, a machine learning technique designed to improve performance in data-scarce settings by training models across multiple tasks. Meta-learning optimises a model for rapid adaptation to the writing style of a new sockpuppet-group. Our results show that meta-learning significantly enhances the precision of predictions compared to pre-trained models, marking an advancement in combating sockpuppetry on open editing platforms. We release a new dataset of sockpuppet investigations to foster future research in both sockpuppetry and meta-learning fields.