Dartmouth team cracks student mental health code

Smartphone sensors predict student wellbeing in pilot study

An application developed at Dartmouth College can predict a student's mental health and academic performance automatically using data collected from sensors in smartphones, The New Republic reports.

Researchers developed a smartphone application that tracked 48 students' location, length of conversations, sleep patterns, and mobility over ten weeks. The app also periodically asked students about their current mood and stress level. Participants took mental health and behavioral surveys at the beginning and end of the study as well.

When researchers compared the data, they found that common mental health issues could be predicted. Low physical activity and infrequent conversations were linked to depression, and low physical activity was linked to loneliness.

Related: Best practices for responding to students of concern

The researchers were surprised by some of the trends they found, including: 

  • Class attendance had no relation to GPA;
  • More frequent conversations were linked to better grades; and
  • Lonely students did not necessarily have fewer conversations. 

Computer science professor Andrew Campbell, the study's lead author, says similar applications could prompt early interventions when a student is struggling academically or emotionally—but has not yet reached out for help. In fact, he did just that for two of his own participants.

As for privacy concerns, Campbell says "it boils down to giving people ownership of their data," adding that ideally students could choose who can see their information (Mirhashem, The New Republic, 9/22).

Next in Today's Briefing

Challenging the binge drinking culture by encouraging students to drink

Next Briefing

  • Manage Your Events
  • Saved webpages and searches
  • Manage your subscriptions
  • Update personal information
  • Invite a colleague