Semantic Classification of Utterances in a Language-Driven Game

  • Kellen Gillespie
  • Michael W. FloydEmail author
  • Matthew Molineaux
  • Swaroop S. Vattam
  • David W. Aha
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 705)


Artificial agents that interact with humans may find that understanding those humans’ plans and goals can improve their interactions. Ideally, humans would explicitly provide information about their plans, goals, and motivations to the agent. However, if the human is unable or unwilling to provide this information then the agent will need to infer it from observed behavior. We describe a goal reasoning agent architecture that allows an agent to classify natural language utterances, hypothesize about human’s actions, and recognize their plans and goals. In this paper we focus on one module of our architecture, the Natural Language Classifier, and demonstrate its use in a multiplayer tabletop social deception game, One Night Ultimate Werewolf. Our evaluation indicates that our system can obtain reasonable performance even when the utterances are unstructured, deceptive, or ambiguous.


Semantic classification Social deception game Tabletop game Goal reasoning 


  1. Aha, D.W. (ed.): Goal Reasoning: Papers from the ACS Workshop (Technical Report GT-IRIM-CR-2015-001), Atlanta, USA. Georgia Institute of Technology, Institute for Robotics and Intelligent Machines (2015)Google Scholar
  2. Azaria, A., Richardson, A., Kraus, S.: An agent for deception detection in discussion based environments. In: Proceedings of the Eighteenth ACM Conference on Computer Supported Cooperative Work & Social Computing, Vancouver, Canada, pp. 218–227. ACM (2015)Google Scholar
  3. Bezier Games. One night ultimate werewolf (2016). Accessed
  4. Chittaranjan, G., Hung, H.: Are you a werewolf? detecting deceptive roles and outcomes in a conversational role-playing game. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, Dallas, USA, pp. 5334–5337. IEEE (2010)Google Scholar
  5. Gillespie, K., Molineaux, M., Floyd, M.W., Vattam, S.S., Aha, D.W.: Goal reasoning for an autonomous squad member. In: Aha, D.W. (ed.) Goal Reasoning: Papers from the ACS Workshop (Technical Report). Atlanta, USA. Georgia Institute of Technology, Institute for Robotics and Intelligent Machines (2015)Google Scholar
  6. Klenk, M., Molineaux, M., Aha, D.W.: Goal-driven autonomy for responding to unexpected events in strategy simulations. Comput. Intell. 29(2), 187–206 (2013)MathSciNetCrossRefGoogle Scholar
  7. Mann, G.S., McCallum, A.: Simple, robust, scalable semi-supervised learning via expectation regularization. In: Proceedings of the Twenty-Fourth International Conference on Machine Learning, Corvallis, USA, pp. 593–600. ACM (2007)Google Scholar
  8. Molineaux, M., Aha, D.W.: Continuous explanation generation in a multi-agent domain. In: Proceedings of the Third Conference on Advances in Cognitive Systems. Cognitive Systems Foundation, Atlanta, USA (2015)Google Scholar
  9. Olney, A.M., Louwerse, M., Matthews, E., Marineau, J., Hite-Mitchell, H., Graesser, A.C.: Utterance classification in AutoTutor. In: Proceedings of the Workshop on Building Educational Applications Using Natural Language Processing at the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics, Edmonton, Canada (2003)Google Scholar
  10. Orkin, J., Roy, D.: Semi-automated dialogue act classification for situated social agents in games. In: Proceedings of the Agents for Games & Simulations Workshop at the Ninth International Conference on Autonomous Agents and Multiagent Systems, Toronto, Canada (2010)Google Scholar
  11. Raiman, N., Hung, H., Englebienne, G.: Move, and I will tell you who you are: Detecting deceptive roles in low-quality data. In: Proceedings of the Thirteenth International Conference on Multimodal Interfaces, Alicante, Spain, pp. 201–204. ACM (2011)Google Scholar
  12. Vattam, S.S., Aha, D.W., Floyd, M.: Case-based plan recognition using action sequence graphs. In: Lamontagne, L., Plaza, E. (eds.) ICCBR 2014. LNCS (LNAI), vol. 8765, pp. 495–510. Springer, Cham (2014). doi: 10.1007/978-3-319-11209-1_35 Google Scholar
  13. Vázquez, M., Carter, E.J., Vaz, J.A., Forlizzi, J., Steinfeld, A., Hudson, S.E.: Social group interactions in a role-playing game. In: Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction, Portland, USA, pp. 9–10. ACM (2015)Google Scholar
  14. Yu, D., Tyshchuk, Y., Ji, H., Wallace, W.A. Detecting deceptive groups using conversations and network analysis. In: Proceedings of the Fifty-Third Annual Meeting of the Association for Computational Linguistics, Beijing, China, pp. 857–866. ACL (2015)Google Scholar
  15. Zhou, L., Sung, Y.-W.: Cues to deception in online chinese groups. In: Proceedings of the Forty-First Hawaii International Conference on Systems Science, Waikoloa, USA (2008)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Kellen Gillespie
    • 1
    • 2
  • Michael W. Floyd
    • 2
    Email author
  • Matthew Molineaux
    • 2
  • Swaroop S. Vattam
    • 3
  • David W. Aha
    • 4
  1. 1.Amazon.Com, Inc.SeattleUSA
  2. 2.Knexus Research CorporationSpringfieldUSA
  3. 3.MIT Lincoln Laboratory (Group 52)LexingtonUSA
  4. 4.Naval Research Laboratory (Code 5514)Washington, DCUSA

Personalised recommendations