Learning macronutrient assessment skills can support improved health outcomes and overall wellbeing. We conducted two Mechanical Turk studies to investigate how users might benefit from the crowd's input in macronutrient assessment education. We first determined whether the wisdom of the crowd alone would provide users with enough insight to arrive at accurate macronutrient estimates. Next, we tested two methods of teaching macronutrient assessment skills (Comparison and Decomposition) and analyzed their effectiveness. Results from these studies indicate that while the crowd alone may not be sufficient to support this type of education, users may yet benefit from access to community-generated photos and labels while they use either the Comparison or Decomposition strategy.

Self-tracking can help personalize self-management interventions for chronic conditions like type 2 diabetes (T2D), but reflecting on personal data requires motivation and literacy. Machine learning (ML) methods can identify patterns, but a key challenge is making actionable suggestions based on personal health data. We introduce GlucoGoalie, which combines ML with an expert system to translate ML output into personalized nutrition goal suggestions for individuals with T2D. In a controlled experiment, participants with T2D found that goal suggestions were understandable and actionable. A 4-week in-the-wild deployment study showed that receiving goal suggestions augmented participants' self-discovery, choosing goals highlighted the multifaceted nature of personal preferences, and the experience of following goals demonstrated the importance of feedback and context. However, we identified tensions between abstract goals and concrete eating experiences and found static text too ambiguous for complex concepts. We discuss implications for ML-based interventions and the need for systems that offer more interactivity, feedback, and negotiation.

We introduce a card game for teaching basic functional programming concepts - specifically maps and filters. The game uses a standard deck of playing cards and the underlying computational concepts can be introduced to students within a one-hour lecture period. We tested this game (informally) with CS-101 students and found it to be an engaging activity. We describe the complete set of instructions for the game and outline future directions of development.

The increasing availability of health data and knowledge about computationally modeling human physiology opens new opportunities for personalized predictions in health. Yet little is known about how individuals interact and reason with personalized predictions. To explore these questions, we developed a smartphone app, GlucOracle, that uses self-tracking data of individuals with type 2 diabetes to generate personalized forecasts for post-meal blood glucose levels. We pilot-tested GlucOracle with two populations: members of an online diabetes community, knowledgeable about diabetes and technologically savvy; and individuals from a low socio-economic status community, characterized by high prevalence of diabetes, low literacy and limited experience with mobile apps. Individuals in both communities engaged with personal glucose forecasts and found them useful for adjusting immediate meal options, and planning future meals. However, the study raised new questions as to appropriate time, form, and focus of forecasts and suggested new research directions for personalized predictions in health.

Americans' health has reached a dangerous obesity epidemic from overconsumption and unhealthy food choices. In response, persuasive games for health encourage healthier lifestyles typically by providing positive reinforcement for the desired behaviors. However, positive reinforcement is only one of the many possibly effective approaches. We explore two types of message framing in a nutrition game, Monster Appetite (MA). In MA, players' choices of high or low calorie snacks impact visual appearance of their monster avatar. MA utilizes two types of health messages: subversive, which encourages players to make unhealthy choices and focuses on costs, and inoculation, which encourages players to eventually defend healthy choices and focuses on benefits. We test message framing's effect by tracking users' purchasing behavior in our online snack shop, Snackazon. The study showed that when positive messages were embedded in MA mixed with negative visuals through the monster avatars, participants exhibited better snack choices post-gameplay.