Computer scientists have already used social media to track flu cases in a population.
Now they want to use it to measure conditions that people often don’t want to talk about except at a distance: mental illness.
By reviewing tweets from users who publicly mentioned a diagnosis or used words linked to certain disorders — like “I just don’t want to get out of bed” — computer scientists like Glen Coppersmith and Mark Dredze say they can quickly and inexpensively collect data on people’s conditions.
“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,” said Mr. Coppersmith, a senior research scientist at Johns Hopkins University.
“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,” he said.
The conditions Mr. Coppersmith and others are interested in following include post-traumatic stress disorder (PTSD), depression, bipolar disorder and seasonal affective disorder.
The data collection does not disclose the names of people who tweet publicly about their conditions, they said. But the findings could help government officials decide where counseling or other care is needed most.
Mr. Coppersmith, Mr. Dredze and colleagues have already reported about how data mining on Twitter showed that PTSD was more prevalent than previously thought at military bases, and that signs of depression are more evident in locations with higher unemployment rates.
While those findings may not be surprising, “analyzing Twitter posts could become a useful yardstick in quickly measuring mental health trends, particularly after dramatic events such as natural disasters and military conflicts,” John Hopkins University said in a statement.
• Cheryl Wetzstein can be reached at cwetzstein@washingtontimes.com.
Please read our comment policy before commenting.