Social media data could be used to detect and track at-risk youth and mental health patients with the help of algorithms developed by researchers at the universities of Ottawa, Alberta, and Montpellier.
Through social media data mining and sentiment analysis, the team can determine a writer's feelings and attitudes and categorize them as positive, negative, or neutral. The tool will focus on finding words commonly attached with negative emotions and variations in social media usage.
"There are some expressions and words that have strong emotional indications but because language is very ambiguous, context is needed," says University of Ottawa researcher Diana Inkpen. "We'll also look at indication of personality based on the text of the messages, the frequency of their messages, their length, and if it changes over time."
Social media data will be collected from publicly available Twitter posts, public medical forums, and open Facebook groups as the team continues to refine the algorithm over the next three years.
The tool would be used by healthcare and psychological professionals to monitor existing patients, with their consent. In the past, social media mining has been used to examine marketing and advertising trends.
From Discover
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found