CS547 Human-Computer Interaction Seminar (Seminar on People, Computers, and Design)
Fridays 11:30am-12:30pm PT · Gates B3 · Open to the public|
Pedja Klasnja
University of Michigan
When and How Design Matters: Investigating How Design Decisions Impact the Effectiveness of Digital Health Interventions
January 24, 2025
Digital health interventions that are based on health-behavior theory are, on average, more effective than interventions that are developed without a robust use of theory. But differences in effectiveness abound even among theory-based interventions. There is growing evidence, both from qualitative research and clinical trials, that how interventions are designed plays a major role in their effectiveness. Of course, that 'design matters' is a commonplace in HCI, but exactly how and when design decisions impact a system's effectiveness is often left unspecified. In this talk, I will review some of the recent research that my colleagues and I have been doing to investigate how differences in design impact the effectiveness of digital health interventions. By drawing on causal modeling and optimization study designs like micro-randomized trials and factorial experiments, we can demonstrate differences in the effectiveness of different designs of an intervention component that implements the same behavior-change technique, such as goal-setting or planning, and articulate specific, testable causal hypotheses for why these differences occur. This type of research, I suggest, can provide guidance for when design is likely to have a significant impact on how well an intervention can support a health behavior like physical activity, and it can build evidence for how best to design digital interventions for different populations and different contexts. |
|