In this paper we study the influence of personality traits in ne-gotiation by using a methodology for automated cognitive be-havior analysis (ACBA). This methodology uses genetic pro-gramming (GP) for hypothesis generation and testing of hu-man behavior with the goal of explaining the underlying men-tal structures guiding people’s actions during a task. ACBA it-eratively generates programs—the hypotheses—capable of ex-plaining the behavior exhibited by an individual during a multi-level, multi-issue, sequential bargaining task against an artifi-cial agent. Our study focuses on the influence of the personal-ity traits of social-value orientation (SVO) and Machiavellian-ism (Mach). The results show that by using ACBA, we are ableto identify differences in the outcomes of programs emergingfrom GP that are consistent with the influences that differentSVO and Mach profiles have in human negotiation behavior.

Humans turn abstract referents and discourse structuresinto gesture using metaphors. The semantic relation be-tween abstract communicative intentions and their phys-ical realization in gesture is a question that has not beenfully addressed. Our hypothesis is that a limited set ofprimary metaphors and image schemas underlies a widerange of gestures. Our analysis of a video corpus sup-ports this view: over 90% of the gestures in the corpus arestructured by image schemas via a limited set of primarymetaphors. This analysis informs the extension of a com-putational model that grounds various communicative in-tentions to a physical, embodied context, using those pri-mary metaphors and image schemas. This model is usedto generate gesture performances for virtual characters.

Theory of Mind (ToM) or mentalizing is the ability to infer mental states of oneself and other agents. Theory of mind plays a key role in social interactions as it allows one to predict other agents' likely future actions by inferring what they may intend or know. However, there is a wide range of ToM skills of increasing complexity. While most people are generally capable of performing complex ToM reasoning such as recursive belief inference when explicitly prompted, there is much evidence that humans do not always use ToM to their full capabilities. Instead, people often fall back to heuristics and biases, such as an egocentric bias that projects one's beliefs and perspective onto the observed agent. We explore which (internal or external) factors may influence the mentalizing processes that humans employ unsolicitedly, i.e., employ without being primed or explicitly triggered. In this paper we present an online study investigating unbalanced decision problems where one choice is significantly better than the other. Our results demonstrate that participant's are significantly less likely to exhibit an egocentric bias in such situations.

A pressing issue in both psychology and agent-modeling com-munities is the inability to account for the wide variance in hu-man variability and individual differences. Added to this is thefurther complexity of changing goals and social meaning in adynamic, sequential interaction. While prior work on artificialagent design has prominently addressed physical cues and non-verbal behavior, there is a lack of emphasis on (1) examiningcues in combination, and (2) assessing judgments of social sit-uational meaning. In the current work, we present an ontologyof physical behavior (Social Kinematics) that accounts for thecombinatorial effects of multiple cues, as well as the changingsocial meaning associated with these different combinations ofcues. Here, we assess individuals social situational judgmentsof multiple combinations of ambiguously-defined virtual agentanimations. Ultimately, this paper provides a potentially usefulframework that has relevance for researchers in social robotics,agent modeling, and cognitive science.