A team of researchers from France and Canada will explore the use of social media data to help detect and monitor individuals potentially at risk of mental health issues

A team of researchers from France and Canada led by Diana Inkpen, a professor of computer science at the University of Ottawa, will explore the use of social media data to help detect and monitor individuals potentially at risk of mental health issues. The project has received a three-year grant from the Natural Sciences and Engineering Research Council of Canada (NSERC).

Social web mining and sentiment analysis for mental illness detection

Social media is everywhere. Internet users are posting, blogging and tweeting about almost everything, including their moods, activities and social interactions. Using novel algorithms, Inkpen and her team, which includes scientists from uOttawa, the University of Alberta and the Université de Montpellier (France), will take the massive data generated through social media and apply social web mining and sentiment analysis methods to detect those at-risk and their mental state.

Inkpen says her team’s goal is to create a set of tools that can be used by doctors, psychologists, school counselors and research groups, among others, to flag concerning patterns in posts made by social media users. But to do this, the team needs massive amounts of existing social media data to sample. [source: CBC News]

We will investigate one application scenario for our predictive model, which will be used to identify at-risk individuals in online communities. The model will also be used by psychologists and psychiatrists to identify variables related to major mental illness.  — Diana Inkpen

Algorithms can pick up strong emotions

The algorithms developed in this project can be adapted for other uses, such as identifying at-risk youth or high school bullying victims.  The research team will partner with the Canadian company Advanced Symbolics, which will collect and sample social media data. Both have expertise in natural language processing, data mining, social media processing and medical informatics, in both English and French. This is a rare asset, as most current research focuses uniquely on English.

Expressions of very negative emotions that are very strong, or appear a lot over longer periods of time, the algorithms can pick up. The algorithm learns from the data.  — Diana Inkpen, comments to CBC News

We speak with University of Ottawa computer science professor Diana Inkpen. Dr. Inkpen is the co-author of Natural Language Processing for Social Media: Synthesis Lectures on Human Language Technologies and director of the Natural Language Processing Lab at University of Ottawa.

680_social media mental health_diana inkpen_march_10_2016_40
Left-click to listen; right-click to save.

audio | #socialmedia #research to detect #mentalillness @UOttawa @CHLYRadio @VIMentalHealth https://t.co/0IONHiMQgC pic.twitter.com/mcDw2pL8mW

— People First Radio (@peoplefirstrad) March 10, 2016

Just how much data do our tweets, likes and photo uploads really generate?