Your tweets show how lonely you are! New study claims use of certain word clusters could help raise red flags
About 47% of Americans often feel alone, left out and lack meaningful connection with others, shows analysis of Twitter posts
Scientists can read your state of mind from what you tweet. A research team has now identified loneliness among Twitter users just by assessing their posts packed in 280 characters.
By dissecting individual tweets, scientists at Penn Medicine have flagged a group of words that are associated with the condition. Their analysis reveals that lonely individuals use Twitter as a medium to voice concerns about mental well-being and their struggles with relationships, substance use, and insomnia. The team of researchers believe their study can help identify such users who require support.
"Social media has the potential to allow researchers and clinicians to passively measure loneliness over time," says study co-author Rachelle Schneider, a research coordinator in the Center for Digital Health. "Through validating our data, we can develop a reliable and accurate tool to do this monitoring."
"Loneliness can be a slow killer, as some of the medical problems associated with it can take decades to manifest," says the study's lead author Dr Sharath Chandra Guntuku, a research scientist at Penn Medicine's Center for Digital Health. "If we are able to identify lonely individuals and intervene before the health conditions associated with the themes we found begin to unfold, we have a chance to help those much earlier in their lives. This could be very powerful and have long-lasting effects on public health," says Dr. Guntuku.
About 47% of Americans — from teenagers to adults — often feel alone, left out and lack meaningful connection with others, according to a study. According to estimated by the US Health Resources Services Administration (HRSA), one in five Americans reportedly feel lonely and socially isolated. Such people face an increased risk of heart disease, arthritis, Type 2 diabetes, dementia and even suicide attempts. The condition has already become an epidemic in the US and other parts of the world.
To come up with a tool to predict loneliness, researchers studied twitter users from Pennsylvania. After the study participants shared their Twitter data, they were given a loneliness survey. The team then set out to study online behavior associated with loneliness.
From their analysis, they found that 6,202 people included words like "lonely" or "alone" more than five times over the period reviewed, from 2012 to 2016. When they compared tweets from the "lonely group" with those who were not, the researchers showed that "lonely" users were more active on Twitter, tweeting nearly twice as much and mostly at night.
The lonely group used phrases from "want somebody" or "no one to" to "smoke," "weed," and/or "drunk" and "I just wanna," "I can't".
"On Twitter, we found lonely users expressing a need for social support, and it appears that the use of expletives and the expression of anger is a sign of that being unfulfilled. Moving forward, we will need to test this in order to determine if one may cause the other — does loneliness cause anger, or vice versa?" says Dr Guntuku.
Among the lonely users, some did not post about loneliness. Instead, they were more likely to engage in conversations, especially by including others' user names (using "@twitter_handle") in their tweets, says the team.
Their next step, say the researchers, is to launch an initiative that could identify loneliness among patients in hospitals and to develop treatment aids for them and their families.
The study has been published in BMJ Open.