Identity and Discourse Among #ActuallyAutistic Twitter Users With Motor Differences

Using #ActuallyAutistic on Twitter for Precision Diagnosis of Autism Spectrum Disorder: Machine Learning Study

BACKGROUND

The increasing use of social media platforms has given rise to an unprecedented surge in user-generated content, with millions of individuals publicly sharing their thoughts, experiences, and health-related information. Social media can serve as a useful means to study and understand public health. Twitter (subsequently rebranded as "X") is one such social media platform that has proven to be a valuable source of rich information for both the general public and health officials. We conducted the first study applying Twitter data mining to autism screening.

OBJECTIVE

This study used Twitter as the primary source of data to study the behavioral characteristics and real-time emotional projections of individuals identifying with autism spectrum disorder (ASD). We aimed to improve the rigor of ASD analytics research by using the digital footprint of an individual to study the linguistic patterns of individuals with ASD.

METHODS

We developed a machine learning model to distinguish individuals with autism from their neurotypical peers based on the textual patterns from their public communications on Twitter. We collected 6,515,470 tweets from users' self-identification with autism using "#ActuallyAutistic" and a separate control group to identify linguistic markers associated with ASD traits. To construct the data set, we targeted English-language tweets using the search query "#ActuallyAutistic" posted from January 1, 2014, to December 31, 2022. From these tweets, we identified unique users who used keywords such as "autism" OR "autistic" OR "neurodiverse" in their profile description and collected all the tweets from their timeline. To build the control group data set, we formulated a search query excluding the hashtag, "-#ActuallyAutistic," and collected 1000 tweets per day during the same time period. We trained a word2vec model and an attention-based, bidirectional long short-term memory model to validate the performance of per-tweet and per-profile classification models. We also illustrate the utility of the data set through common natural language processing tasks such as sentiment analysis and topic modeling.

RESULTS

Our tweet classifier reached a 73% accuracy, a 0.728 area under the receiver operating characteristic curve score, and an 0.71 F1-score using word2vec representations fed into a logistic regression model, while the user profile classifier achieved an 0.78 area under the receiver operating characteristic curve score and an F1-score of 0.805 using an attention-based, bidirectional long short-term memory model. This is a promising start, demonstrating the potential for effective digital phenotyping studies and large-scale intervention using text data mined from social media.

CONCLUSIONS

Textual differences in social media communications can help researchers and clinicians conduct symptomatology studies in natural settings.

Social Media as a Tool for Understanding the Role of Motor Differences in Neurodivergent Identity and Lived Experience

Social media offers an exciting opportunity for the field of motor development and behavior research. With platforms such as Twitter offering access to historical data from users' public bios and posts, there is untapped potential to examine community perspectives on the role of motor differences in identity and lived experience. Analysis of online discourse offers advantages over traditional qualitative methods like structured interviews or focus groups, including a less-contrived setting, global geographic and cultural representation, and ease of sampling. The aim of this special section is to present a pipeline for harvesting and analysis of Twitter data related to users' identities and discourse characteristics, specifically situated in the context of motor development and behavior. This pipeline is demonstrated in two independent studies, one on autistic users and one on developmental coordination disorder (DCD)/dyspraxic users. These studies demonstrate the utility of Twitter data for research on neurodivergent and disabled people's perspectives on their motor differences, and whether they are expressed as part of their identity. Implications of results are discussed for each study, as well as in the larger context of future research using a variety of approaches to analysis of social media data, including those from predominantly image- and video-based platforms.