Accepted for/Published in: JMIR Mental Health
Date Submitted: Nov 27, 2018
Date Accepted: Aug 21, 2019
(closed for review but you can still tweet)
Caring or creepy? A survey of public opinions on using social media content for identifying users with depression and targeting mental health-care advertising.
ABSTRACT
Background:
Depression is a common disorder but is under-diagnosed and under-treated in the UK National Health Service. Charities and third sector organizations offer mental health services but can struggle to promote these to individuals who need them. By analyzing social media (SM) content using machine-learning techniques, it may be possible to identify which SM users are currently experiencing low mood, thus enabling the targeted advertising of mental health services to individuals who would benefit from them.
Objective:
This study aimed to understand social media users’ opinions of analysis of social media content for depression and targeted advertising on social medial for mental health services.
Methods:
An online, mixed-methods, cross-sectional survey was administered to SM users over the age of 16. It asked participants about their demographics, their usage of SM, their history of depression, and presented structured and open-ended questions on views of SM content being analysed for depression and views on receiving targeted advertising for mental health services.
Results:
183 participants completed the survey, 62.3% of whom had previously experienced depression. Participants indicated that they posted less during low moods and they believed their SM content would not reflect their depression. They could see the benefits of the analysis for depression in principle but did not believe the risks to privacy outweighed these benefits. A majority would not consent for such analysis to be carried out on their data and considered it intrusive and exposing.
Conclusions:
In a climate of distrust of social media platforms’ usage of personal data, participants in this survey did not perceive that the benefits of targeting adverts for mental health services to individuals analysed as having depression would outweigh the risks to privacy. Future work in this area should proceed with caution and should engage stakeholders at all stages to maximize the transparency and trustworthiness of such research endeavours.
Citation
