Communications of the ACM
Algorithm Trained to Detect Unhappiness on Social Networks
The research team spent two years working on a deep learning model that identifies the five needs described by William Glasser's Choice Theory: Survival, Power, Freedom, Belonging, and Fun.
Credit: psychologytoday.com
Scientists at Spain's Universitat Oberta de Catalunya have created a deep learning algorithm that analyzes social network content to help diagnose users' potential for mental health problems.
The researchers trained the model to identify image content and to categorize text by assigning labels proposed by psychologists, who compared the results to a database containing roughly 30,000 images, captions, and comments.
The researchers analyzed 86 Instagram profiles in Spanish and Persian, and the results of their analysis supported the idea that human choices do not always stem from one basic need.
The researchers suggested, "Studying data from social networks that belong to non-English speaking users could help build inclusive and diverse tools and models for addressing mental health problems in people with diverse cultural or linguistic backgrounds."
From Universitat Oberta de Catalunya News (Spain)
View Full Article
Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA
No entries found