Stephen M Schueller1, Diana M Steakley-Freeman2, David C Mohr2, Elad Yom-Tov3. 1. Department of Psychological Science, University of California, Irvine, Irvine, CA, USA; Department of Preventive Medicine, Northwestern University, Chicago, IL, USA. Electronic address: s.schueller@uci.edu. 2. Department of Preventive Medicine, Northwestern University, Chicago, IL, USA. 3. Microsoft Research, Herzeliya, Israel.
Abstract
BACKGROUND: The expanding amount of information available from our use of technologies has led researchers to explore how this information can aid in the detection of mental health issues. We expand on past work in this area by exploring how browsing histories might be able to predict perceived barriers to psychological treatment. METHODS: We obtained 10 days of browsing history data for 255 respondents as well as assessments of Perceived Barriers to Psychological Treatments and depression, the Patient Health Questionnaire. RESULTS: We found that browsing histories enabled high performance classification of people with high levels of perceived barriers to psychological treatments (AUC average of 0.86). LIMITATIONS: Our high classification accuracy does not help understand why different features within the browsing histories are useful to classify people according to browsing history. We also look at people who decided to contribute their browsing history but the use of this data more generally presents additional ethical questions. CONCLUSIONS: Browsing histories might be useful to classify people's barriers to seeking psychological treatment. It is clinically relevant to find those who perceive barriers to seeking treatment to better design ways to address those concerns and help them find treatment.
BACKGROUND: The expanding amount of information available from our use of technologies has led researchers to explore how this information can aid in the detection of mental health issues. We expand on past work in this area by exploring how browsing histories might be able to predict perceived barriers to psychological treatment. METHODS: We obtained 10 days of browsing history data for 255 respondents as well as assessments of Perceived Barriers to Psychological Treatments and depression, the Patient Health Questionnaire. RESULTS: We found that browsing histories enabled high performance classification of people with high levels of perceived barriers to psychological treatments (AUC average of 0.86). LIMITATIONS: Our high classification accuracy does not help understand why different features within the browsing histories are useful to classify people according to browsing history. We also look at people who decided to contribute their browsing history but the use of this data more generally presents additional ethical questions. CONCLUSIONS: Browsing histories might be useful to classify people's barriers to seeking psychological treatment. It is clinically relevant to find those who perceive barriers to seeking treatment to better design ways to address those concerns and help them find treatment.
Authors: Michael Mullarkey; Mallory Dobias; Jenna Sung; Isaac Ahuvia; Jason Shumake; Christopher Beevers; Jessica Schleider Journal: JMIR Ment Health Date: 2022-04-12