Using Twitter to Detect Psychological Characteristics of Self-Identified Persons With Autism Spectrum Disorder: A Feasibility Study

Abstract

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: More than 3.5 million Americans live with autism spectrum disorder (ASD). Major challenges persist in diagnosing ASD as no medical test to diagnose these disorders exist. Digital phenotyping holds promise to helping guide in the clinical diagnoses and screening of ASD. Objective: To explore the feasibility of using the online social media platform Twitter to detect psychological and behavioral characteristics of self-identified persons with autism. Methods: Data from Twitter was retrieved from 152 self-identified users with autism or ASD and 182 randomly selected control users from March 22, 2012 to July 20, 2017. A comparative textual analysis of tweets about repetitive and obsessive-compulsive behavioral characteristics typically associated with autism was conducted between groups. Common emotional characteristics of persons with autism such as fear, paranoia and anxiety were also examined between groups through textual analysis. Timing of tweets was compared between users with autism and control users to identify patterns in communication. Results: Users with autism/ASD posted a significantly higher frequency of tweets related to the specific repetitive behavior of counting compared to control users (P<.001). Textual analysis of obsessive-compulsive behavioral characteristics such as fixate, excessive, and concern were significantly higher among users with autism compared to the control group (P<.001). Emotional terms related to fear, paranoia and anxiety were also tweeted at a significantly higher rate among users with autism compared to control users (P<.001). Users with autism posted a smaller proportion of tweets during time intervals of 00:00–05:59 (P<.001), 06:00–11:59 (P<.001), and 18:00-23.59 (P<.001), and a greater proportion of tweets from 12:00-17:59 (P<.001) compared to control users. Conclusions: Social media may be a valuable resource for observing unique psychological characteristics of self-identified persons with autism. Collecting and analyzing data from these digital platforms may afford opportunities to identify characteristics of autism and assist in the diagnosis or verification of autism disorders. This study highlights the feasibility of leveraging digital data for gaining new insights about various health conditions.