Researchers at the University of Sao Paulo are using artificial intelligence (AI) and Twitter to create anxiety and depression prediction models. The models could detect signs of these illnesses before clinical diagnosis. Preliminary findings from the model suggest the possibility of detecting the likelihood of a person developing depression based solely on their social media friends and followers. The first step involved constructing a database, called SetembroBR, of information relating to a corpus of 47 million publicly posted Portuguese texts and the network of connections between 3,900 Twitter users. The second step, still in progress, has provided some preliminary findings, such as the possibility of detecting the likelihood of a person developing depression based solely on their social media friends and followers.
As seen in the coverage by researchers, work is currently underway to develop anxiety and depression prediction models using artificial intelligence (AI) and Twitter. The aim of this project is to detect signs of these illnesses before clinical diagnosis. The researchers, based at the University of Sao Paulo (USP) in Brazil, have revealed that preliminary findings from the model suggest the possibility of detecting the likelihood of a person developing depression based solely on their social media friends and followers. These findings have been published in the journal Language Res and Evaluation.
While there are multiple studies involving natural language processing (NLP) focused on depression, anxiety, and bipolar disorder, most of these have analyzed English texts and did not match the profiles of Brazilians, As seen in the coverage by the researchers. Therefore, the first step in this study involved constructing a database, called SetembroBR, of information relating to a corpus of 47 million publicly posted Portuguese texts and the network of connections between 3,900 Twitter users. These users had reportedly been diagnosed with or treated for mental health problems before the survey. The tweets were collected during the COVID-19 pandemic.
“First, we collected timelines manually, analyzing tweets by some 19,000 users, equivalent to the population of a village or small town. We then used two datasets, one for users who reported being diagnosed with a mental health problem and another selected at random for control purposes. We wanted to distinguish between people with depression and the general population,” said Ivandre Paraboni, last author of the article and a professor at USP.
Because people with mental health problems tended to follow certain accounts such as discussion forums, influencers, and celebrities who publicly acknowledge their depression, the study also collected tweets from friends and followers. The second step, still in progress, has provided some preliminary findings, such as the possibility of detecting the likelihood of a person developing depression based solely on their social media friends and followers, without taking their own posts into account.
Following pre-processing of the corpus to maintain original texts by removing non-standard characters, the researchers deployed deep learning (AI) to create four text classifiers and word embeddings (context-dependent mathematical representations of relations between words) using models based on bidirectional encoder representations.
The potential implications of this study are significant. If successful, the use of AI and Twitter could revolutionize the way in which mental health disorders are diagnosed and treated, enabling healthcare professionals to intervene earlier and provide more targeted care. The study is still in its early stages, but the researchers are hopeful that their findings will lead to the development of more effective diagnosis and treatment methods for mental health disorders.
Accordingly, the work being carried out by the researchers at the University of Sao Paulo is incredibly promising. By using AI and Twitter to detect early signs of mental health disorders, it is hoped that this technology could help to improve the lives of millions of people around the world. As the study progresses, it will be interesting to see how the findings are developed and how they could be applied in clinical settings.