#Mafia

• 6 players, 4 town vs 2 mafia
  
• Nightless - no nights, no night actions, no night kills
  
• Sensor - at the beginning of the next day phase, I will state in the OP exactly how many mafia were on the lynch wagon the previous day.
  
• Special mechanic - the first mafia to be lynched gets a bomb ability - he chooses 1 person to die with him.
  
• No other roles.
  

• Normal rules apply, no screenshotting PMs, no outside comms, etc.
  
• UNVOTEing is encouraged, not required
  
• 24 hour DP cycles; no NP
  
• Majority lynch
  
• No-lynching results in mafia being awarded a kill
  

In this project, we use deep learning to detect deception through online conversations in the interaction-based party game Mafia. We present various neural network frameworks (LSTM, bidirectional LSTM, CNN) to generate predictions of deceptive text. The results of this paper suggest the capability of neural network architectures to effectively detect deception in the Mafia setting, and offer qualitative analysis in agreement with current deception research findings.

We have trained tensorflow frameworks based on unidirectional LSTM, bidirectional LSTM, as well as CNN, that successfully perform deception detection on online Mafia game interactions using the Mafiascum dataset [3]. All three models performed above baseline accuracy (81.6%), with 88.8% (unidirectional LSTM), 94.7% (bidirectional LSTM), and 94.9% (CNN). This suggests that deeplearning techniques may be able to effectively identify linguistic cues that signal deception.