Analyzing the contribution of different passively collected data to predict Stress and Depression
This work addresses mental health assessment using passive data, but it is incremental as it focuses on evaluating existing feature types rather than introducing new methods.
The study analyzed the contribution of various passively collected sensor data types, such as WiFi and Phone Log features, to predict daily self-reported stress and PHQ-9 depression scores, finding that WiFi and Phone Log features provided significant predictive information.
The possibility of recognizing diverse aspects of human behavior and environmental context from passively captured data motivates its use for mental health assessment. In this paper, we analyze the contribution of different passively collected sensor data types (WiFi, GPS, Social interaction, Phone Log, Physical Activity, Audio, and Academic features) to predict daily selfreport stress and PHQ-9 depression score. First, we compute 125 mid-level features from the original raw data. These 125 features include groups of features from the different sensor data types. Then, we evaluate the contribution of each feature type by comparing the performance of Neural Network models trained with all features against Neural Network models trained with specific feature groups. Our results show that WiFi features (which encode mobility patterns) and Phone Log features (which encode information correlated with sleep patterns), provide significative information for stress and depression prediction.