Hunting for Troll Comments in News Community Forums

TL;DR

This paper investigates opinion manipulation trolls in Bulgarian news forums, developing classifiers that can identify paid and mentioned trolls with over 81% accuracy, contributing to automated detection of online manipulation.

Contribution

It introduces two classifiers for detecting opinion manipulation trolls based on leaked contracts and user mentions, achieving over 81% accuracy.

Findings

Classifiers distinguish paid trolls from non-trolls with 81-82% accuracy.

Classifiers identify mentioned trolls with 81-82% accuracy.

Definitions of trolls are validated through effective classification.

Abstract

There are different definitions of what a troll is. Certainly, a troll can be somebody who teases people to make them angry, or somebody who offends people, or somebody who wants to dominate any single discussion, or somebody who tries to manipulate people's opinion (sometimes for money), etc. The last definition is the one that dominates the public discourse in Bulgaria and Eastern Europe, and this is our focus in this paper. In our work, we examine two types of opinion manipulation trolls: paid trolls that have been revealed from leaked reputation management contracts and mentioned trolls that have been called such by several different people. We show that these definitions are sensible: we build two classifiers that can distinguish a post by such a paid troll from one by a non-troll with 81-82% accuracy; the same classifier achieves 81-82% accuracy on so called mentioned troll vs. non-troll posts.