Excited to share that my StoryMap paper received an Honorable Mention (top 5% of the submissions) at CHI 2021.

StoryMap is a family informatics app that uses social storytelling and reflection for promoting exercise among low-SES families. We found that both data and stories in health informatics are important means of health promotion, but they work in their own unique ways.

Herman Saksono, Carmen Castaneda-Sceppa, Jessica Hoffman, Magy Seif El-Nasr, Andrea G. Parker. 2021. StoryMap: Using Social Modeling and Self-Modeling to Support Physical Activity Among Low-SES Families. In CHI Conference on Human Factors in Computing Systems Proceedings (CHI 2021). ACM, New York, NY. (PDF)

I will present this paper at CHI in two sessions:

I also provide a short article summarizing the takeaways of this paper on Medium: Stories are just powerful as data in personal health informatics.

Additionally, I will participate in two CHI workshops. The first workshop is Realizing AI in Healthcare in which I will present my paper Algorithmic Patient Matching in Peer Support Systems for Hospital Inpatients:

Peer support in inpatient portal systems can help patients to manage their hospital experiences, namely through social modeling of similar patients’ experiences. In this position paper, I will begin by providing a theoretical foundation of social modeling and peer matching. Then I will present matching strategies for algorithmic tools to match patients by their similarities, as well as the challenges and consequences that will surface when such a system is deployed in the wild. These technosocial complexities show that algorithmic matching in this context is non-trivial. Finally, based on the evidence and theories known thus far, I will present two recommendations on how to algorithmically match patient that will support social modeling, align with human cognition, and reduce the risk of injustices in clinical settings.

Watch the video presentation below:

The second workshop is Artificially Intelligent Technology for the Margins, in which I submitted a position paper titled Transformative-fair AI for Addressing the Societal Origins of Marginalization:

This paper introduced the Transformative-fair framework for understanding the scope of impact of algorithmic tools for supporting marginalized communities. In contrast to Reformative-fair, algorithmic tools that meet Transformative-fair criteria seek to counter the societal origin of marginalization itself. More specifically, by amplifying the community assets (e.g., skills and knowledge in the community) and aspirations, strengthening social relationships, and supporting internally driven community efforts.

See you at CHI 2021!

CHI 2021 Honorable Mention
Tagged on:     

Leave a Reply

Your email address will not be published.

This site uses Akismet to reduce spam. Learn how your comment data is processed.