A new study now finds that the language used in Facebook posts can be used to identify medical conditions. According to a study conducted by the University of Pennsylvania School of Medicine and Stony Brook University, analysing social media posts could help spot signs of diabetes, anxiety, depression and psychosis.
The researchers used artificial intelligence (AI) software to analyse language through Facebook posts of around 1,000 patients from which they reached the conclusion. Their revelations could be used to gain insight into a person's lifestyle choices and their emotions, which could also help with any potential treatment.
Speaking about the study, lead author Dr Raina Merchant said the hope is that the "insights gleaned from these posts could be used to better inform patients and providers about their health."
She further added since social media posts are often about someone's life choices and experience, or how they are feeling, it could provide information about disease management and the escalation of problems.
The study saw researchers using an automated data collection technique to analyse the volunteers' entire Facebook posting history. Participants also agreed to have electronic medical records linked to their profiles. The researchers used three models, one which focused on the Facebook data only, and one which used demographics such as age and sex and a third which combined both datasets.
According to the experts, frequent use of words such as drink' or 'bottle' could be used to predict alcohol abuse, while the use of hostile language was found to be an indicator of drug abuse and psychoses.
The new study follows close in the heels of one by the same researchers which suggested that social media posts could help diagnose depression and according to the lead author it could be valuable for those who regularly use social media as it could allow healthcare providers to review social media records to get an insight into a person's life in order to help them.
Comments
0 comment