Leveraging Spatio-Temporal Data Science Techniques on Non-Stop Smart Sensing to Improve Health and Well-Being
Abstract
When high school students leave their homes for a college education, the students oftenface enormous changes and challenges in life, such as meeting new people, more responsibilitiesin life, and being away from family and their comfort zones. These sudden changes often lead to anelevation of stress and anxiety, which can affect a student’s health and well-being. Researchers areincreasingly relying on smartphones to monitor individuals (such as college students) continuouslyto identify various factors that can affect students’ behavioral patterns (such as communicationbehaviors) that may be associated with their health, well-being, and academic success. In thiswork, we use different visualizations and statistical techniques to find various geographical placesand temporal factors that affect students’ communication patterns (in terms of phone call durationand frequency) to foster the design and delivery of future smartphone-based health interventions;thereby, potentially helping students adjust to college life. From our detailed analysis of an 18-month dataset collected from a cohort of 464 freshmen, we obtain insights on communicationpattern variations during different temporal contexts, e.g., epochs of a day, days of a week, theparts of a semester, social events, and in various geographical contexts (i.e., places of interest).Finally, we also obtain a negative correlation of −0.29 between physical activity and phone callduration, which can help provide guided feedback to improve future health behaviors.
Subject Area
Behavioral Sciences|Health sciences|Educational psychology|Communication
Recommended Citation
Kim, Yugyeong, "Leveraging Spatio-Temporal Data Science Techniques on Non-Stop Smart Sensing to Improve Health and Well-Being" (2021). ETD Collection for Fordham University. AAI28495849.
https://research.library.fordham.edu/dissertations/AAI28495849
