The Application of User Event Log Data for Mental Health and Wellbeing Analysis

Many digital interaction technologies, including web-based interventions,
smartphone applications, and telephone helplines, can provide a basis for
capturing real time data of interactions between the user and the system. Such
data is recorded in the form of log files, which records user events that range
from simple keystrokes on a computer, user activated sensor data or
duration/frequency of phone calls. These interactions can provide rich datasets
amenable to user data analytics using machine learning and other analytics
techniques. This data analysis can highlight usage patterns and user behaviours
based on their interaction with the technology. User log data analysis can be
descriptive statistics (what users have done), predictive analytics (what events
will happen) and prescriptive (what action to take given a predicted event or
outcome). This can also be thought of as spanning across different levels of user
analytics from hindsight, insight and foresight. Predictive analytics are used with
log data to provide predictions on future user behaviour based on early usage
behaviours. Event logs are objective regarding usage, but usage may not
correlate with the level of the system’s user experience. Hence, ecological
momentary assessment (EMA) of the user experience can be used augment user
log data. Nevertheless, with the emergence of health applications and other appbased
health services, we consider how user event logs can be specifically used
within the mental health domain. This can provide beneficial insights into how
users interact with mental health e-services, which can provide an indication of
their current and future mental state.