View - ResearchGate

54 Socially Intelligent Agentstive architecture capable of modeling a variety of individual differences (e.g.,affective states, personality traits, etc.) [5], and (2) developing an adaptive userinterface capable of recognizing and adapting to the user’s affective and beliefstate (e.g., heightened level of anxiety, belief in imminent threat, etc.) [4].In this chapter we focus on the area of affective adaptation and describe anAffect and Belief Adaptive Interface System (ABAIS) designed to compensatefor performance biases caused by users’ affective states and active beliefs. Theperformance bias prediction is based on empirical findings from emotion research,and knowledge of specific task requirements. The ABAIS architectureimplements a four-phase adaptive methodology: (1) assessing user affect andbelief state; (2) identifying their potential impact on performance; (3) selectinga compensatory strategy; and (4) implementing this strategy in terms ofspecific GUI adaptations. ABAIS provides a generic adaptive framework forexploring a variety of user assessment methods (e.g., knowledge-based, selfreports,diagnostic tasks, physiological sensing), and GUI adaptation strategies(e.g., content- and format-based). We outline the motivating psychologicaltheory and empirical data, and present preliminary results from an initialprototype implementation in the context of an Air Force combat task. We concludewith a summary and outline of future research and potential applicationsfor the synergistic application of the affect-adaptive and affect and personalitymodeling methodologies within SIA architectures.2. Selecting Affective States And Personality TraitsThe first step for both the modeling and the adaptation research goals is toidentify key affective and personality traits influencing behavior. The affectivestates studied most extensively include anxiety, positive and negative affect,and anger. The effects of these states range from influences on distinct informationprocesses (e.g., attention and working memory capacity, accuracy,and speed; memory recall biases), through autonomic nervous system manifestations(e.g., heart rate, GSR), to visible behavior (e.g., facial expressions,approach vs. avoidance tendencies, etc.) [9, 7, 1]. A wide variety of personalitytraits have been studied, ranging from general, abstract behavioraltendencies such as the Five Factor Model or “Big 5” (Extraversion, EmotionalStability, Agreeableness, Openness, Conscientiousness) and “Giant 3”(Approach behaviors, Inhibition behaviors, Aggressiveness) personality traits,through psychodynamic / clinical traits (e.g., narcissistic, passive-aggressive,avoidant, etc.), to characteristics relevant for particular type of interaction (e.g.,style of leadership, etc.) [3, 8]. Our initial primary focus in both the modelingand the adaptation research areas was on anxiety, aggressiveness, and obsessiveness.