The Community for Technology Leaders
2015 International Conference on Affective Computing and Intelligent Interaction (ACII) (2015)
Xi'an, China
Sept. 21, 2015 to Sept. 24, 2015
ISSN: 2156-8111
ISBN: 978-1-4799-9952-1
pp: 222-228
Natasha Jaques , Media Lab, Massachusetts Institute of Technology, Cambridge, MA 02139
Sara Taylor , Media Lab, Massachusetts Institute of Technology, Cambridge, MA 02139
Asaph Azaria , Media Lab, Massachusetts Institute of Technology, Cambridge, MA 02139
Asma Ghandeharioun , Media Lab, Massachusetts Institute of Technology, Cambridge, MA 02139
Akane Sano , Media Lab, Massachusetts Institute of Technology, Cambridge, MA 02139
Rosalind Picard , Media Lab, Massachusetts Institute of Technology, Cambridge, MA 02139
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.
INDEX TERMS
Stress, Stress measurement, Physiology, Atmospheric measurements, Particle measurements, Accelerometers, Energy measurement
CITATION

N. Jaques, S. Taylor, A. Azaria, A. Ghandeharioun, A. Sano and R. Picard, "Predicting students' happiness from physiology, phone, mobility, and behavioral data," 2015 International Conference on Affective Computing and Intelligent Interaction (ACII), Xi'an, China, 2015, pp. 222-228.
doi:10.1109/ACII.2015.7344575
98 ms
(Ver 3.3 (11022016))