# The Mafiascum Dataset: A Large Text Corpus for Deception Detection

arXiv: https://arxiv.org/abs/1811.07851 · HTML: https://mlsanity.com/paper/1811.07851/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2018.

## Built on by (most cited first, 9 of 9)

- [Putting the Con in Context: Identifying Deceptive Actors in the Game of Mafia](https://mlsanity.com/paper/2207.02253/) (2022)
- [Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games](https://mlsanity.com/paper/2506.05309/) (2025)
- [Can Factual Statements be Deceptive? The DeFaBel Corpus of Belief-based Deception](https://mlsanity.com/paper/2403.10185/) (2024)
- [UNIDECOR: A Unified Deception Corpus for Cross-Corpus Deception Detection](https://mlsanity.com/paper/2306.02827/) (2023)
- [Can lies be faked? Comparing low-stakes and high-stakes deception video datasets from a Machine Learning perspective](https://mlsanity.com/paper/2211.13035/) (2022)
- [Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games](https://mlsanity.com/paper/2601.13709/) (2026)
- [CSP4SDG: Constraint and Information-Theory Based Role Identification in Social Deduction Games with LLM-Enhanced Inference](https://mlsanity.com/paper/2511.06175/) (2025)
- [How Entangled is Factuality and Deception in German?](https://mlsanity.com/paper/2409.20165/) (2024)
- [A persistent accuracy ceiling in automated verbal deception detection](https://mlsanity.com/paper/2610.12118/) (2026)

## Abstract (arXiv)

Detecting deception in natural language has a wide variety of applications, but because of its hidden nature there are currently no public, large-scale sources of labeled deceptive text. This work introduces the Mafiascum dataset [1], a collection of over 700 games of Mafia, in which players are randomly assigned either deceptive or non-deceptive roles and then interact via forum postings. Over 9000 documents were compiled from the dataset, which each contained all messages written by a single player in a single game. This corpus was used to construct a set of hand-picked linguistic features based on prior deception research, as well as a set of average word vectors enriched with subword information. A logistic regression classifier fit on a combination of these feature sets achieved an average precision of 0.39 (chance = 0.26) and an AUROC of 0.68 on 5000+ word documents. On 50+ word documents, an average precision of 0.29 (chance = 0.23) and an AUROC of 0.59 was achieved. [1] https://bitbucket.org/bopjesvla/thesis/src