Researchers from the Open University of Catalonia (UOC) algorithm that can distinguish users social media those who are unhappy with analyzing texts and images They share a tool they hope will be useful in helping diagnose potential mental health problems.
The UOC’s research also revealed that: Spanish-speaking users are more likely to mention problems than English-speaking users about their relationships when they feel bad.
The algorithm, which is trained on searches on Instagram, Facebook, and Twitter, is based on William Glasser’s choice theory, in which five basic needs are at the root of all human behavior: survival, power, freedom, belonging and fun.
According to experts, these needs influence which image we choose to upload to our Instagram profile.
“How we manifest ourselves in social networks can provide useful information about behaviors, personalities, perspectives, motives and needs,” said Mohammad Mehdi Dehshibi, who coordinates research in the AI ​​for Human Health (AIWELL) group. UOC’s Computer, Multimedia and Telecommunications Studies.
The researchers worked on the deep learning model for two years. Defines the five needs identified by Glasser, using multimodal data such as images, text, bio or geolocation.
To perform the study, published in the journal IEEE Transactions on Affective Computing, they analyzed 86 Instagram profiles posted in Spanish and Persian.
get old neural networks and databasesThe experts trained an algorithm to identify the content of images and classify text content, assigning them different labels suggested by psychologists, and compared the results to a database of more than 30,000 images, titles, and comments.
Mehdi Dehshibi, also a researcher at the imBody Research Laboratory of the University of Madrid Carlos III and the Non-Traditional Computing Laboratory of the University of the West of England in Bristol, explains this with an example: “Imagine a cyclist climbing a mountain and a selfie at the top. or you can choose to share group picture.
“If you choose selfie, we perceive the need for power, but if you choose the other, we can conclude that the person is looking for a way to satisfy the need for belonging as well as having fun.‘, he explains.
Researchers also found that Spanish-speaking users were more likely than English-speaking users to talk about relationship problems when they were feeling down.
” examining social media data “Belonging to non-English speaking users can help create inclusive and diverse tools and models for addressing mental health issues in people of different cultural or linguistic backgrounds,” they write.
The authors believe their research can help improve preventative measures when someone is diagnosed with a mental disorder, from identifying the problem to improving treatments.
Source: Informacion
Barbara Dickson is a seasoned writer for “Social Bites”. She keeps readers informed on the latest news and trends, providing in-depth coverage and analysis on a variety of topics.