Socially Interactive Agents as Cobot Avatars: Developing a Model to Support Flow Experiences and Well-Being in the Workplace

This study evaluates a socially interactive agent to create an em-bodied cobot. It tests a real-time continuous emotional modelingmethod and an aligned transparent behavioral model, BASSF (bore-dom, anxiety, self-efficacy, self-compassion, flow). The BASSF modelanticipates and counteracts counterproductive emotional experi-ences of operators working under stress with cobots on tedioustasks. The flow experience is represented in the three-dimensionalpleasure, arousal, and dominance (PAD) space. The embodied cov-atar (cobot and avatar) is introduced to support flow experiencesthrough emotion regulation guidance. The study tests the model'smain theoretical assumptions about flow, dominance, self-efficacy,and boredom. Twenty participants worked on a task for an hour,assembling pieces in collaboration with the covatar. After the task,participants completed questionnaires on flow, their affective expe-rience, and self-efficacy, and they were interviewed to understandtheir emotions and regulation during the task. The results suggestthat the dominance dimension plays a vital role in task-relatedsettings as it predicts the participants' self-efficacy and flow. How-ever, the relationship between flow, pleasure, and arousal requiresfurther investigation. Qualitative interview analysis revealed thatparticipants regulated negative emotions, like boredom, also with-out support, but some strategies could negatively impact well-beingand productivity, which aligns with theory.