The team worked on this deep learning model for two years. The researchers relied on American psychiatrist William Glasser’s Choice Theory, which describes five basic needs central to all human behaviour — survival, power, freedom, belonging and fun. They say these needs have an influence on the images we choose to upload on social media platforms such as Facebook, Twitter or Instagram. The study also revealed that Spanish-speaking users were more likely to mention relationship problems on social media when they feel depressed than English-speaking users.
“How we present ourselves on social media can provide useful information about behaviours, personalities, perspectives, motives and needs,” Mohammad Mahdi Dehshibi, who led this study, said in a statement.
Dehshibi and his team of researchers analysed 86 Instagram profiles, in both Spanish and Persian, for the study published in the journal IEEE Transactions on Affective Computing. They believe that their research can help improve preventive measures, ranging from identification to improved treatment when a person has been diagnosed with a mental health disorder.
But how does the algorithm work? Dehshibi explains this by citing an example of a cyclist riding up a mountain. Once at the top, whether the person chooses to share a selfie or a group photo can help understand the person’s mental state. If the person chooses a selfie, it’s perceived as a need for power. If they choose the other option, it is concluded that the person is looking for more than just fun, but also a way to satisfy their need for belonging.
Robinhood Stocks Rally as FTX Founder Acquires 7.6 Percent Stake in Crypto-Stock Exchange