CUBISM: belief, anomaly and social constructs Yorick Wilks, Micah Clark, Tomas By, Adam Dalton, and Ian Perera {ywilks, mclark, tby, adalton, iperera} @ihmc.us Florida Institute for Human and Machine Cognition (IHMC) 15 Osceola Avenue, Ocala, FL, USA 34471 Abstract. We introduce the CUBISM system for the analysis and deep understanding of multi-participant dialogues. CUBISM brings together two typically separate forms of discourse analysis: semantic analysis and sociolinguistic analysis. In the paper proper, we describe and illustrate major components of the CUBISM system, and discuss the challenge posed by the system’s ultimate purpose, which is to automatically detect anomalous changes in participants’ expressed or implied beliefs about the world and each other, including shifts toward or away from cultural and community norms. Keywords: natural language understanding; belief modeling; sociolinguistics; discourse analysis Yorick Wilks is a Senior Research Scientist at the Florida Institute for Human and Machine Cognition (IHMC) and formerly Professor of Artificial Intelligence at the University of Sheffield. He is the author of ten books on aspects of Artificial Intelligence and Natural Language Processing and a Fellow of the Association for Computing Machinery. Micah H. Clark is a Research Scientist at the Institute for Human & Machine Cognition (IHMC). Micah is interested in cognitive and social psychology, philosophy of mind, and machine ethics. Prior to joining IHMC, Micah spent 15 years at the NASA Jet Propulsion Laboratory. Micah received his PhD in Cognitive Science from Rensselaer Polytechnic Institute (RPI) in 2010 and his B.S. in Computer Science and Philosophy in 1999, also from RPI. Tomas By is a Research Scientist at IHMC. He has a MA degree in Computational Linguistics (Gothenburg University) and a PhD in Computer Science (Sheffield University). Before joining IHMC in 2013, he held research posts at Hamburg University, Munich Technical University, Lisbon New University, and Carnegie Mellon University in Qatar. Adam Dalton joined IHMC as a research associate in 2012. His primary interests are in linguistic technologies and cyber security. Adam was previously the Information Architecture technical lead on the Launch Control System project at NASA's Kennedy Space Center. Adam has a B.Sc. in Honours Computer Science (McGill) and a M.Sc. in Modeling and Simulation (University of Central Florida). Ian Perera is a PhD student in Computer Science at the University of Rochester. His primary research area is on Artificial Intelligence with a focus on Natural Language. He also has a M.S. in Computer Science from the Rochester and a D.S.E in Digital Media Design from the University of Pennsylvania.