Evaluating the Effectiveness of Health Recommendations based on Sensor data to Support College Students' Well-being
2024-06
Loading...
View/Download File
Persistent link to this item
Statistics
View StatisticsJournal Title
Journal ISSN
Volume Title
Title
Evaluating the Effectiveness of Health Recommendations based on Sensor data to Support College Students' Well-being
Authors
Published Date
2024-06
Publisher
Type
Thesis or Dissertation
Abstract
Stress management is difficult for college students as college can be very demanding. Stress can contribute to serious health issues, if not timely addressed, in an individual and is a critical problem. Recent studies have highlighted the growing prevalence and severity of mental health issues among college students, exacerbated by factors such as the COVID-19 pandemic and social isolation. The interest in examining technological interventions to support stress management is on the rise. Prior work has proposed a system that generates AI based recommendations for daily stress prevention/management. The recommendation system takes into account user's preferences for activities and self-reported well-being surveys to recommend stress relievers. However, this approach is limited to one snapshot event and relies on self-report data. To address this problem, this thesis focuses on using wearable sensors to get a continuous perspective of the user's day to improve the recommendation systems' performance and user experience. We integrated wearable sensor data (i.e., Garmin activity tracker watch) within the recommendation system to track the user's daily activity levels along with the user's stress and sleep levels. We thus conducted three rounds of testing with different prioritization levels, to evaluate the recommendation system with sensor data. The evaluation study demonstrated that the model performed optimally in the second testing round with an accuracy of 94\%, validating our hypothesis by predicting the category of activities that users have not engaged in. This supports our goal of fostering diverse activity recommendations to encourage well-being. Furthermore, the user study of 20 college students revealed that the sensor-integrated system significantly improved their motivation towards self-care, with participants notably preferring the personalized, actionable health recommendations derived from real-time data. Our findings suggest that continuous monitoring via wearable sensors enhances the effectiveness of recommendation systems in stress management, offering substantial benefits in promoting healthier lifestyle choices among college students.
Keywords
Description
University of Minnesota M.S. thesis. June 2024. Major: Computer Science. Advisor: Jomara Sandbulte. 1 computer file (PDF); vii, 82 pages.
Related to
Replaces
License
Series/Report Number
Funding information
Isbn identifier
Doi identifier
Previously Published Citation
Other identifiers
Suggested citation
Putta, Mamatha. (2024). Evaluating the Effectiveness of Health Recommendations based on Sensor data to Support College Students' Well-being. Retrieved from the University Digital Conservancy, https://hdl.handle.net/11299/265101.
Content distributed via the University Digital Conservancy may be subject to additional license and use restrictions applied by the depositor. By using these files, users agree to the Terms of Use. Materials in the UDC may contain content that is disturbing and/or harmful. For more information, please see our statement on harmful content in digital repositories.