Multimodal Analysis of Impressions and Personality in Human-Computer and Human-Robot Interactions

Abstract

This talk will focus on automatic prediction of impressions and inferences about traits and characteristics of people based on their multimodal observable behaviours in the context of human-virtual character and human-robot interactions. The first part of the talk will introduce and describe the creation and evaluation of the MAPTRAITS system that enables on-the-fly prediction of the widely used Big Five personality dimensions (i.e., agreeableness, openness, neuroticism, conscientiousness and extroversion) from a third-vision perspective. A novel approach for sensing and interpreting personality is through a wearable camera that provides a first-person vision (FPV) perspective and therefore enables the acquisition of information about the users' true behaviours and intentions. Accordingly, the second part of the talk will introduce computational analysis of personality traits and interaction experience through first-person vision features in a human-robot interaction context. The perception of personality is also crucial when the interaction takes place over distance. Tele-operated robot avatars, in which an operator's behaviours are portrayed by a robot proxy, have the potential to improve interactions over distance by transforming the perception of physical and social presence, and trust. However, having communication mediated by a robot changes the perception of the operator's appearance, behaviour and personality. The third and last part of the talk will therefore present a study on how robot mediation affects the way the personality of the operator is perceived, analysed and classified, and will discuss the implications our research findings have for autonomous and tele-operated robot design.