This Is How Twitter Uncovers Mental Illness Trends


Twitter is proving itself as a valuable tool, especially for researchers at John Hopkins University, who recently used tweets to detail trends of mental illness in the United States.

These researchers looked through more than 8 billion tweets, using a computer algorithm that searched for language related to mental illness as well as users who publicly mentioned their diagnosis.

The computer algorithm searched for specific words and phrases, including cues associated with anxiety and insomnia. For example, the algorithm tracked tweets about not wanting to get out of bed.

This technique and algorithm was previously used by John Hopkins when tracking outbreaks of the flu last year, which proved their method successful.

Researchers hope to eventually share this information with public health officials, perhaps helping address how some illnesses get treated, as well as what specific illnesses are prevalent in certain parts of the country, indicating where help is needed. Mental illness is a lot harder to track than other diseases, especially considering the stigma attached to it.

However, when many people take to social media, they feel the urge to talk openly about their struggles, including those with mental illnesses.

"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, a Johns Hopkins senior research scientist. "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."

Of course, this process doesn't take the place of more traditional methods of gathering data, but it does complement those methods.

"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 counseling and other care is needed most," says Mark Dredze, an assistant research professor in the Whiting School of Engineering's Department of Computer Science. "It could point to places where many veterans may be experiencing PTSD, for example, or to towns where people have been traumatized by a shooting spree or widespread tornado damage."

In their earlier findings, researchers found  higher incidents of depression from tweeters in areas hit hardest by unemployment. They also saw post-traumatic stress disorder in areas with high veteran populations.

[Photo Credit: Andrew Mager/Flickr]

ⓒ 2018 All rights reserved. Do not reproduce without permission.
Real Time Analytics