Predicting students' happiness from physiology, phone, mobility, and behavioral data

Abstract

In order to model students' happiness, we apply machine learning methods to data collected from undergrad students monitored over the course of one month each. The data collected include physiological signals, location, smartphone logs, and survey responses to behavioral questions. Each day, participants reported their wellbeing on measures including stress, health, and happiness. Because of the relationship between happiness and depression, modeling happiness may help us to detect individuals who are at risk of depression and guide interventions to help them. We are also interested in how behavioral factors (such as sleep and social activity) affect happiness positively and negatively. A variety of machine learning and feature selection techniques are compared, including Gaussian Mixture Models and ensemble classification. We achieve 70% classification accuracy of self-reported happiness on held-out test data.

Fig. 1

An example of typical SCRs

Fig. 2

Example of a participant’s SMS data for 4 consecutive days. Note that there is a large increase in SMS during the negative day, which is followed by a return to a positive day

Fig. 3

GMM fitted to location data from one participant. The black points are latitude longitude coordinates, while the yellow are the means of the Gaussian components representing the ROIs. The contours mark the probability distribution induced by the model.