Discovering Hidden Structure in High Dimensional Human Behavioral Data via Tensor Factorization
This work addresses the challenge of analyzing high-dimensional behavioral data for researchers in psychology or health, but it is incremental as it applies an existing method to a new dataset.
The paper tackled the problem of uncovering low-dimensional structure in noisy, multimodal human behavioral data from wearables and other sources by applying non-negative tensor factorization to the StudentLife dataset. It demonstrated that this method successfully discovered clusters of individuals with higher academic performance and frequent leisure activities, with latent temporal patterns validated against ground truth data.
In recent years, the rapid growth in technology has increased the opportunity for longitudinal human behavioral studies. Rich multimodal data, from wearables like Fitbit, online social networks, mobile phones etc. can be collected in natural environments. Uncovering the underlying low-dimensional structure of noisy multi-way data in an unsupervised setting is a challenging problem. Tensor factorization has been successful in extracting the interconnected low-dimensional descriptions of multi-way data. In this paper, we apply non-negative tensor factorization on a real-word wearable sensor data, StudentLife, to find latent temporal factors and group of similar individuals. Meta data is available for the semester schedule, as well as the individuals' performance and personality. We demonstrate that non-negative tensor factorization can successfully discover clusters of individuals who exhibit higher academic performance, as well as those who frequently engage in leisure activities. The recovered latent temporal patterns associated with these groups are validated against ground truth data to demonstrate the accuracy of our framework.