Stacy Marsella
Location: (Marina del Rey, CA)
Personal Research Web Page: http://ict.usc.edu/~marsella
Keywords: computational models of human behavior, social simulation, virtual humans, emotion, cognition, theory of mind, decision-theory, machine learning, cognition, nonverbal behavior, animation
Posted on: Saturday, May 30th, 2009
Broad Research Area: AI / Machine Learning / Robotics / Vision, Computer Science Education / Educational Technology, Graphics / Visualization, Other, Social Computing / Social Informatics
Research Interests:
The research goals of USC’s Computational Emotion Group and ICT’s Social Simulation Lab are to study and model human behavior. Our work on human behavior modeling includes computational models of human emotion, decision-making, theory of mind reasoning and nonverbal behavior.
The Computational Emotion Group also studies the application of these models to the design of virtual humans, life-like facsimiles of humans that look and act like humans and can interact with humans using spoken dialog much as humans interact with each other. Current efforts of the Emotion Group include validating the EMA model of emotion against human data, machine learning approaches to deriving models of nonverbal behavior, the role of physiological processes in emotion and the animation of expressive behavior within the SmartBody virtual human animation system.
The Social Simulation Lab works on modeling and simulating human social interaction, at a more aggregate level (groups, cities, etc.). Ongoing research includes tractable approaches to modeling of theory of mind reasoning and decision-theoretic, descriptive models of human-like decision-making. We also study automated and data-driven approaches to validate and facilitate authoring of large scale social simulations.
