Smartphone app knows when you're feeling blue

A newly developed smartphone app collects and analyses various data to predict when you're feeling depressed, stressed or lonely.

Michelle Starr Science editor
Michelle Starr is CNET's science editor, and she hopes to get you as enthralled with the wonders of the universe as she is. When she's not daydreaming about flying through space, she's daydreaming about bats.
Michelle Starr
3 min read

Dmitry Kalinin, CC BY 2.0

Just as physical health is important, so too is mental health -- deeply so. And, just as smartphone apps exist that can help you take care of your diet, sleep and fitness, now we're starting to see others that want to help your mind stay healthy.

StudentLife, developed by a team at Dartmouth College led by computer science professor Andrew Campbell, taps into several smartphone features to gauge how you might be feeling.

The app was loaded onto the Android phones of 48 students, who used them for a period of 10 weeks, after completing a surveys to establish a physical and mental health baseline.

The app then used the phone's sensor data to monitor behaviour; for example, accelerometers to gauge when and how the students are moving; the GPS to gauge where the student is and how long they spend there; how often and how long they talk on the phone; and other peripheral data, such as how long the students sleep and between which hours, and light levels.

The students also completed small surveys daily to gauge mood and stress levels, and monitor diet. The app used learning algorithms to adapt to each user's behavioural patterns, in order to better sense anomalies. Over the 10-week study period, the team collected over 52.6GB of data -- and found that this data correlated the students' mental health with their academic performance over the course of the term.

Overall, the results revealed that, generally, more sleep and a higher number of conversations lowers the likelihood of depression, as does in-person social interaction; and that a higher level of physical activity correlated with a lower likelihood of loneliness. And, interestingly, social interaction seemed to have a stronger correlation with academic performance than class attendance.

"What is the impact of stress, mood, workload, sociability, sleep and mental health on academic performance?" Professor Campbell said. "Much of the stress and strain of student life remains hidden. In reality faculty, student deans, clinicians know little about their students in and outside of the classroom. Students might know about their own circumstances and patterns but know little about classmates. To shine a light on student life, we developed the first of a kind smartphone app and sensing system to automatically infer human behaviour."

Campus isn't the only potential application for StudentLife. The team also proposes that it could be used to reduce stress levels and monitor productivity in the workplace, alerting users to behaviour that correlates with stress and depression -- if privacy concerns can be adequately addressed.

"We purposely provided students with no feedback in this first study because we didn't want to use StudentLife as a behavioural change tool. We simply wanted to 'record' their time on campus," Professor Campbell said. "Providing feedback and intervention is the next step. For example, we might inform students of risky behavior, such as partying too much, poor levels of sleep for peak academic performance, poor eating habits or being too socially isolated."

You can read the full paper online on the Dartmouth University website.