Recent advances in pervasive computing enable the collection of personal health-related data using various sensors in daily life. Subjective well-being (SWB) considers how people experience and evaluate their lives and specific domains and activities in their lives. Human behavior modeling and analysis, particularly the quantification of SWB, is still challenging, as there are variations in its definition and measurement. Psychology literature defines different perspectives for SWB, such as hedonic, eudaimonic, or psychologic. In this paper, we propose a model for predicting an individual’s SWB from a psychological perspective. We use the data of The NetHealth study, a heterogeneous data set of 577 student participants from the University of Notre Dame. It contains data about individuals’ daily activities collected via smart wristbands, social relationships monitored through smartphones, and personality traits obtained from surveys. We develop a multi-class classifier based on commonly accepted machine learning algorithms. The results enable us to predict an individual’s well-being almost with an accuracy of 80%. We show that such a pervasive application can be offered as a personalized well-being assistant.
Predicting Subjective Well-being from a Psychological Perspective
2023
Article (Journal)
Electronic Resource
Unknown
Metadata by DOAJ is licensed under CC BY-SA 1.0
Travel Time and Subjective Well-Being
Online Contents | 2013
|Travel Time and Subjective Well-Being
Transportation Research Record | 2013
|Subjective well-being and travel: retrospect and prospect
Online Contents | 2018
|Subjective well-being and travel: retrospect and prospect
Online Contents | 2018
|