In recent years, there has been a lot of talk about the damage that social media can do to social media. In fact, last year Lush announced that it was leaving social media platforms such as Facebook and Instagram due to its concern for mental health, especially among young people.
All of this has led a group of researchers from the Universitat Oberta de Catalunya (UOC) to launch an algorithm that seeks to help psychologists diagnose mental problems through what is published on social media.
"How we present ourselves on social media can provide useful information about behaviours, personalities, perspectives, motives and needs," says Mohammad Mahdi Dehshibi , who led this research in the AI for Human Well-being (AIWELL) group at the UOC's Faculty of Informatics, Multimedia and Telecommunications.
The learning model used by the algorithm is based on the five needs of qatar number data human behavior from William Glasser's theory of choice. Survival, power, freedom, belonging and fun are the aspects that it takes into account.
The algorithm is able to identify the content of images in order to assign different labels proposed by psychologists . They compared the results with a database of more than 30,000 images, captions and comments.
All of this was used to develop a study, in which they analyzed 86 Instagram profiles. One of the conclusions points out that Spanish-speaking users are more likely than English-speaking users to mention problems in their relationships when they feel depressed.
“Studying social media data from non-English speaking users could help build inclusive and diverse tools and models to address mental health issues in people from diverse cultural or linguistic backgrounds,” they write.