Modeling social inference in virtual agents

摘要: Social judgment is a social inference process whereby an agent singles out individuals to blame or credit for multi-agent activities. Such inferences are key aspect of intelligence that underlie planning, learning, natural language pragmatics and computational models emotion. With the advance interactive systems need designing socially aware interfaces interact with people, it increasingly important model this human-centric form inference. Based on psychological attribution theory, paper presents general framework automate based agent’s causal knowledge observations interaction.