was successfully added to your cart.

Subscribe to our newsletter

& get a copy of our new e-book
  • This field is for validation purposes and should be left unchanged.

Study Shows Twitter Usage Expresses ADHD

By Sharath Chandra Guntuku, Post-Doctoral Researcher, University of Pennsylvania

In short, what is the study about?

We computationally analyzed about 1.3 million tweets written by 1,399 Twitter users with self-reported diagnoses of ADHD, comparing their language and online posting patterns to those of a control set of users matched by age, gender and period of activity.

What would be the most important take-home messages from the study?

Twitter can reveal quite a bit about people with ADHD — they tend to tweet out messages related to lack of focus and self-regulation, they tend to post more about the past, and late at night between 12am-6am. These insights could provide clues to design more effective treatments and be used as complementary feedback for patients suffering from ADHD.

How are these findings important in practice?

While many of our findings confirm what is already known in the ADHD literature, other findings are novel and will help clinicians to generate hypotheses regarding the behavior and propensities of individuals with ADHD. For example, our study highlighted that language of users with ADHD is indicative of more hedging themes, descriptors of mental, physical, and emotional exhaustion, which is also consistent with recent findings of elevated fatigue and lower self-efficacy in adults with ADHD compared with healthy control. Interestingly, we also found that many Twitter users with ADHD talked about using marijuana. This was validated by our co-author, Russell Ramsay, who has observed this in his conversations with the ADHD patients he treats.

However, our finding that ADHD adults use social media to a greater extent as compared to healthy individuals is a phenomenon that has not been verified by clinicians yet; although it seems logical that such an online platform should be desirable to individuals who, as a group, have difficulties delaying gratification. Similarly, we found that this group is more likely to post during hours typically devoted to sleep, and this too is not established in clinical studies yet. Our study opens up a great new avenue to gain a more comprehensive understanding of the symptoms and behavior of ADHD patients, which when automatically summarized can immensely aid clinicians in their brief 30- or 60-minute interactions with patients.

What other studies can be recommended to further an understanding/application of the findings?

The current study reflects the use of social media as a novel source of information about the experience of adults with ADHD. Further studies need to investigate some of the novel findings of this study for ongoing research as well as potential screening and clinical uses — for example in developing simple intervention and personalized feedback tools monitoring stress and anxiety of a person based on their social media activity. Also, we need to work on tuning the performance of the predictive model to be useful as a diagnostic risk assessment tool, which it currently is not.

Link to the Research Paper

Guntuku, S. C., Ramsay, J. R., Merchant, R. M., & Ungar, L. H. (2017). Language of ADHD in adults on social media. Journal of Attention Disorders. Advance online publication.  DOI: 1087054717738083.

About Sharath Chandra Guntuku, Post-doctoral Researcher, University of Pennsylvania

Alternative Text

Sharath Chandra Guntuku is a post-doctoral researcher in the Perelman School of Medicine and in the Department of Computer and Information Science at the University of Pennsylvania. Prior to joining Penn, he completed his PhD studies on building machine learning algorithms to model users’ personality in multimedia preferences at the School of Computer Science and Engineering at Nanyang Technological University, Singapore. He received his bachelor's degree in computer science from BITS-Pilani, India in 2013. His current research aims to leverage large-scale social media image and text data to model social health outcomes and psychological traits.

Sharath Chandra Guntuku on the Web
More on: ADHD, Research
Latest update: December 29, 2017