Painting a Digital Portrait of Insomnia Using Tweets

Photo via Shutterstock user Minerva Studio.

Photo via Shutterstock user Minerva Studio.

Do you have trouble sleeping at night? Well, you’re not alone. Between 50 and 70 million Americans reportedly struggle with insomnia and other chronic sleep issues – that’s equal to approximately one-fifth of the country’s population. According to statistics from the National Sleep Foundation and Center for Disease Control and Prevention, sleep deprivation can significantly compromise one’s safety and health. In addition to decreasing alertness and level of productivity, chronic sleep disorders can contribute to diabetes, cardiovascular disease and depression.

Recent research from Boston Children’s Hospital and Merck suggests patients with sleep disorders may also be at a greater risk of psychosocial issues. In a study published earlier this month in the Journal of Medical Internet Research, a group of doctors was able to construct the foundation of a “digital phenotype” of a Twitter user with insomnia – establishing an interesting relationship between social media usage and sleep issues.

As part of the 2014 Boston Children’s Hospital-Merck collaboration on social media and sleep, Jared Hawkins, PhD; David McIver, PhD; and John Brownstein, PhD; came together to develop what they call “a baseline profile” of a social media user suffering from sleep deprivation.

“Sleep deprivation and chronic sleep disorders are not well understood,” Brownstein said in a press release. “We wanted to see if we could use new forms of online data, such as Twitter, to characterize the sleep-disordered individual and possibly uncover new, previously-undescribed populations of patients suffering sleep problems.”

The team compiled two groups of virtual samples from publically available anonymized data:

  1. 896 active Twitter users whose tweets contained sleep-related words or hashtags (e.g. “insomnia,” #teamnosleep) and/or the names of common sleep aids or medications (e.g. Ambien)
  2. 934 active Twitter users whose tweets did not contain sleep-related terms

After analyzing each user’s profile, the team took into consideration the user’s age, total number of tweets, total number of followers and people followed, number of favorite tweets, length of time on Twitter, average number of tweets per day, location and time zone.  They also looked at the time of day and measured the tweets’ average sentiment (positive, neutral, negative).

With this information, the researchers built a comprehensive profile of a Twitter user with sleep issues.  Compared to a Twitter user without sleep issues, this user has fewer followers, follows fewer people and posts few tweets per day on average. However, these users are more active on Twitter in the evening and night (between 6:00 p.m. and 5:59 a.m.) and are more active on weekends and early weekdays as well. They also are more likely to post tweets with negative sentiment, indicating that sleep-disordered users could be more at-risk for psychosocial issues.

“These findings are preliminary and observational only, and need to be studied further,” Brownstein cautioned. “But they suggest that social media can be a useful addition to our toolkit for studying the patient experience and behavioral epidemiology of sleep disorders.”

Population-level research on sleep disorders typically comes from surveys, such as the Behavior Risk Factor Surveillance System; however, this method requires extensive amounts of time, resources, and expenses. Utilizing social media as a tool to identify individuals exhibiting insomnia symptoms could potentially help improve patient diagnosis, as this method is fast, cost-effective and customizable.  User analytics and demographics from other platforms, such as Facebook, could further supplement these results.

Nicole Yang

Nicole Yang

    Nicole Yang is an editorial intern at MedTech Boston. She is currently a rising senior at Amherst College, where she studies Neuroscience. During the academic year, Nicole is the Managing Editor of The Amherst Student and has also worked as a Chemistry laboratory teaching assistant. Outside of the classroom, she enjoys playing squash and practicing yoga. Follow her on Twitter @Nicole_Yang12.

    Leave a Reply

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

    Follow us!

    Send this to friend