Exposing Paid Opinion Manipulation Trolls

TL;DR

This paper addresses the challenge of automatically detecting paid opinion manipulation trolls online by proposing a method that leverages user reputation based on multiple mentions, and demonstrates effective classification results.

Contribution

It introduces a novel approach to identify paid trolls using reputation-based labeling, overcoming the lack of extensive training data.

Findings

Reputation-based labeling effectively identifies paid trolls.

Classifiers trained on mentioned vs. non-trolls also detect paid trolls.

The method achieves high accuracy in distinguishing troll types.

Abstract

Recently, Web forums have been invaded by opinion manipulation trolls. Some trolls try to influence the other users driven by their own convictions, while in other cases they can be organized and paid, e.g., by a political party or a PR agency that gives them specific instructions what to write. Finding paid trolls automatically using machine learning is a hard task, as there is no enough training data to train a classifier; yet some test data is possible to obtain, as these trolls are sometimes caught and widely exposed. In this paper, we solve the training data problem by assuming that a user who is called a troll by several different people is likely to be such, and one who has never been called a troll is unlikely to be such. We compare the profiles of (i) paid trolls vs. (ii)"mentioned" trolls vs. (iii) non-trolls, and we further show that a classifier trained to distinguish (ii) from (iii) does quite well also at telling apart (i) from (iii).