Computational Cognitive Models of Behavior Change in the Real World and at Scale

Psychology calls itself the science of behavior, but some have lamented that “cognitive psychology [has] never had much to say about the meaningful activities people perform in their daily lives, nor have they really intended to.” In this presentation, Dr. Pirolli discusses two threads of research on computational cognitive models of human behavior change in the ecology of everyday life. The first thread of research concerns models of health behavior change occurring in multi-week, in-the-world, experiments using mobile health applications designed to promote physical activity, stress reduction, and improved nutrition habits. These computational models, built in the ACT-R cognitive architecture, provide an integrated account of goal intentions, implementation intentions, self-efficacy, motivation, self-affirmation, and habit strengthening underlying more than a half dozen behavior change techniques. The second thread of research expands on ACT-R models of behavior change to address how humans responded to the COVID-19 pandemic. Heterogeneous behavioral responses over time and geographical regions depend on the individual beliefs and information consumption patterns of populations. To address the need for more precise and accurate epidemiological models, we are researching Psychologically Valid Agent models of human responses to epidemic information and non-pharmaceutical interventions during the pandemic.

Duration: 1 - 4 hours

Introductory

Free