Estimating Anxiety based on individual level engagements on YouTube Google Search Engine
share
Anxiety disorder is one of the most prevalent mental health conditions, arising from complex interactions of biological and environmental factors and severely interfering one's ability to lead normal life activities. Current methods for detecting anxiety heavily rely on in-person interviews. Yet, such mental health assessments and surveys can be expensive, time consuming, and blocked by social stigmas. In this work, we propose an alternative way to identify individuals with anxiety and further estimate their levels of anxiety using private online activities histories from YouTube and Google search engine, platforms that are used by millions of people daily. We ran a longitudinal study and collected multiple rounds of anonymized YouTube and Google search log data from volunteering participants, along with their clinically validated ground-truth anxiety assessment scores. We then engineered explainable features that capture both the temporal and semantic aspects of online behaviors. We managed to train models that not only identify individuals having anxiety disorder but also can predict the level of anxiety comparable to the gold standard Generalized Anxiety Disorder 7-item scores with a mean square error of 1.87 based on the ubiquitous individual-level online engagements.
READ FULL TEXT
