Putting the Con in Context: Identifying Deceptive Actors in the Game of Mafia

TL;DR

This paper investigates how speaker roles influence language in Mafia games, demonstrating that models can identify deceptive players based solely on language cues and that auxiliary training improves detection accuracy.

Contribution

It introduces a new dataset and framework for analyzing language in Mafia games, showing that role-specific language patterns can be effectively modeled and used for deception detection.

Findings

Language differs between honest and deceptive players.

Models trained on auxiliary tasks outperform standard classifiers.

Features identified can assist players in detecting deception.

Abstract

While neural networks demonstrate a remarkable ability to model linguistic content, capturing contextual information related to a speaker's conversational role is an open area of research. In this work, we analyze the effect of speaker role on language use through the game of Mafia, in which participants are assigned either an honest or a deceptive role. In addition to building a framework to collect a dataset of Mafia game records, we demonstrate that there are differences in the language produced by players with different roles. We confirm that classification models are able to rank deceptive players as more suspicious than honest ones based only on their use of language. Furthermore, we show that training models on two auxiliary tasks outperforms a standard BERT-based text classification approach. We also present methods for using our trained models to identify features that distinguish between player roles, which could be used to assist players during the Mafia game.