Amii researcher Nawshad Farruque, a graduate student under the supervision of Amii Fellows Osmar Zaïane and Randy Goebel, has developed an ML model that can detect early signs of depression in text.

UAlberta Science News, Folio, Techxplore and Global News reported that the model was developed using writing samples of self-identified depressed individuals, as detailed in the paper “Augmenting Semantic Representation of Depressive Language: From Forums to Microblogs” published at the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Database (ECML-PKDD).

“The outcome of our study is that we can build useful predictive models that can accurately identify depressive language,” said Farruque in the interview. “While we are using the model to identify depressive language on Twitter, the model can be easily applied to text from other domains for detecting depression.”

As depression globally affects more than 264 million people of all ages (according to the World Health Organization), the applications for an algorithm of this nature are immense; from detecting early signs of depression in youth through social media posts to monitoring the mental health of seniors through conversational chatbots.