The language used in Facebook posts can be used to identify some medical condition, new research has claimed.
A new study suggests that analysing the content of posts to the social network could help spot signs of conditions such as diabetes, anxiety, depression and psychosis.
Experts used artificial intelligence (AI) software to analyse the language in Facebook posts from around 1,000 test patients.
What they learned could be used to gain an insight into a person’s lifestyle choices and how they were feeling, which could also help with any potential treatment.
Researchers from the University of Pennsylvania School of Medicine and Stony Brook University are behind the study.
Lead author Dr Raina Merchant said: ‘This work is early, but our hope is that the insights gleaned from these posts could be used to better inform patients and providers about their health.
‘As social media posts are often about someone’s lifestyle choices and experiences or how they’re feeling, this information could provide additional information about disease management and exacerbation.’
The researchers used an automated data collection technique to analyse the entire Facebook posting history of those who agreed to take part and to share their data.
Participants also agreed to have electronic medical records linked to their profiles.
Three different models were then built to asses the data – one which focused on the Facebook data only, one which used demographics such as age and sex and a third which combined both datasets.
Looking into 21 different conditions, the researchers claim that all 21 were predictable from Facebook data alone.
The regular 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 researchers said.
It follows a previous study carried out last year by some of the same team which suggested that social media posts could help predict a diagnosis of depression.
Those behind the latest study said it was difficult to predict how widespread an opt-in version of the system for patients could be, but Dr Merchant said would it ‘could be valuable’ for those who use social media on a regular basis.
‘For instance, if someone is trying to lose weight and needs help understanding their food choices and exercise regimens, having a healthcare provider review their social media record might give them more insight into their usual patterns in order to help improve them,’ she said.
Dr Merchant is due to lead a trial later this year which will ask patients to directly share their social media content with their health care provider, which the researchers say will offer insight into how willing patients are to use their online posts as part of healthcare.
HOW DOES ARTIFICIAL INTELLIGENCE LEARN?
AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn.
ANNs can be trained to recognise patterns in information – including speech, text data, or visual images – and are the basis for a large number of the developments in AI over recent years.
Conventional AI uses input to ‘teach’ an algorithm about a particular subject by feeding it massive amounts of information.
Practical applications include Google’s language translation services, Facebook’s facial recognition software and Snapchat’s image altering live filters.
The process of inputting this data can be extremely time consuming, and is limited to one type of knowledge.
A new breed of ANNs called Adversarial Neural Networks pits the wits of two AI bots against each other, which allows them to learn from each other.
This approach is designed to speed up the process of learning, as well as refining the output created by AI systems.
