What if your profile picture on Instagram says a lot more than you thought? It is in any case the starting point of an exciting work carried out by researchers from the Open University of Catalonia.
Mohammad Mahdi Dehshibi, the main author of this study, is indeed convinced: ” How we present ourselves on social media can provide useful information about behaviors, personalities, perspectives, motivations and needs ».
Selfie or group photo? On Instagram, the details are revealing
The scientists therefore worked on an algorithm operating on the model of deep learning. To build their artificial intelligence, they relied on a solid database of 30,000 images, captions and comments posted on Instagram. To avoid cultural bias, accounts of Spanish-speaking and Persian-speaking people were chosen.
Their analysis is based on the concept of choice theory proposed by the American psychiatrist William Glasser. According to him, human beings have five needs in common: belonging, power, freedom, pleasure, and survival. Therefore, and according to the personalities of each of us, some of these needs are sought after at some point and it is precisely this state of mind that it would be possible to detect by closely observing our photos posted on Instagram .
To explain the logic of this analysis, Mohammad Mahdi Dehshibi specifies: “ Imagine a cyclist climbing a mountain and at the top they can choose between sharing a selfie and a group photo. If he chooses the selfie, we perceive a need for power, but if he chooses the other option, we can conclude that the person is not only looking for fun but also to satisfy his need to belong. ».
Although we do not have any figures, this work in any case provides a very stimulating line of work and could in particular make it possible to improve the diagnosis and treatment of people suffering from mental health problems.
Note that this is clearly not the first time that technology has been used to manage this kind of problem. To cite just one example, we told you two years ago about this application developed by Canadian researchers which allows the mental health of its users to be monitored.
