Communications of the ACM
Scientists Build Model to Detect Early Signs of Depression in Text
A machine learning model developed at Canada's University of Alberta can identify early signs of depression in written text.
Credit: MIT News
Scientists at Canada's University of Alberta (UAlberta) have created a machine learning model that can identify linguistic clues indicating early signs of depression in written text, like Twitter messages.
The team developed the English-language model from writing samples by individuals who identify as depressed in online depression forums; the algorithm was trained to detect depressive language in tweets.
UAlberta's Nawshad Farruque said, "This is the first study to show that depressive language has a specific linguistic representation. We demonstrate that it is possible to identify it, transfer it, and further use it for depressive language detection tasks."
From University of Alberta
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found