Mining Twitter data opens a window on mental health

December 15, 2014 − by Suzanne Elvidge − in Big data, Big data in research, Data analytics, Data mining − No Comments

Social media generates a lot of information every day, from pictures of cats to discussions of science and politics. However, it can also been used to monitor outbreaks of disease, including infectious diseases such as flu and the winter vomiting virus. In some of the latest reports on the medical use of data from social media, computer scientists at Johns Hopkins have announced that they may be able to use data mining as a tool to capture information on a number of common mental illnesses from tweets, including post-traumatic stress disorder (PTSD), depression, bipolar disorder and seasonal affective disorder.

The team monitored tweets from people who mentioned their diagnosis, and used computer algorithms to analyse more than 8 billion tweets to track language cues that can be linked to a variety of disorders. These included language patterns associated with these ailments, such as words linked with anxiety and insomnia, or phrases such as ‘I just don’t want to get out of bed’.

“With many physical illnesses, including the flu, there are lots of quantifiable facts and figures that can be used to study things like how often and where the disease is occurring, which people are most vulnerable and what treatments are most successful,” says Glen Coppersmith of Johns Hopkins. “But it’s much tougher and more time-consuming to collect this kind of data about mental illnesses because the underlying causes are so complex and because there is a long-standing stigma that makes even talking about the subject all but taboo.”

They used data analysis techniques to mine the data, and gain information in disease prevalence. The findings were validated by observations such as PTSD being more prevalent at military installations that frequently deployed during the recent Iraq and Afghanistan conflicts, or signs of depression being more common in locations with higher unemployment rates. The Johns Hopkins research has potential to speed the rate of collection of mental health data, and cut the costs, compared with traditional methods such as surveys, while maintaining patient anonymity.

“We’re not aiming to replace the long-standing survey methods of tracking mental illness trends. We believe our new techniques could complement that process. We’re trying to show that analyzing tweets could uncover similar results, but could do so more quickly and at a much lower cost,” says Coppersmith.

According to the researchers, their goal is to be able share information about the prevalence of mental illness with treatment providers and public health officials.

“Using Twitter to get a fix on mental health cases could be very helpful to health practitioners and governmental officials who need to decide where counselling and other care is needed most,” says Mark Dredze of the Whiting School of Engineering’s Department of Computer Science.

Post a Comment

Your email address will not be published. Required fields are marked *