Gabarron, Elia; Dorronzoro, Enrique; Rivera-Romero, Octavio; Denecke, Kerstin (2024). Understanding Emotional Dynamics in Autism Social Media Communities In: Mantas, John; Hasman, Arie; Demiris, George; Saranto, Kaija; Marschollek, Michael; Arvanitis, Theodoros N.; Ognjanović, Ivana; Benis, Arriel; Gallos, Parisis; Zoulias, Emmanouil; Andrikopoulou, Elisavet (eds.) Digital Health and Informatics Innovations for Sustainable Health Care Systems. Studies in Health Technology and Informatics: Vol. 316 (pp. 1901-1905). Amsterdam: IOS Press 10.3233/SHTI240804
|
Text
MIE_Autism_EmotionalDynamics.pdf - Published Version Available under License Creative Commons: Attribution-Noncommercial (CC-BY-NC). Download (245kB) | Preview |
Searches for autism on social media have soared, making it a top topic. Social media posts convey not only plain text, but also sentiments and emotions that provide insight into the experiences of the autism community. While sentiment analysis categorizes overall sentiment, emotion analysis provides nuanced insights into specific emotional states. The objective of this study is to identify emotions in posts related to autism and compare the emotions specifically contained in posts that include the hashtag #ActuallyAutistic with those that do not. Methods: We extracted a sample of X' posts related to autism and used DistilBERT to assign one out of six emotions (sadness, joy, love, anger, fear, surprise) to each post. Results: We have analyzed a total of 414,287 posts, 98,602 (23.8%) of those included the hashtag #ActuallyAutistic. The most common expressed emotion was joy, which was expressed in 52.5% of the posts, followed by sadness, identified in 28.6% of the posts. 12% of the posts expressed fear, 4.9% reflected anger, 1.1% showed love, and 0.9% expressed surprise. Posts tagged as #ActuallyAutistic showed less joy (27.1% vs. 60.4% in posts without this hashtag, p<0.001) and more sadness (52.7% vs. 21.1% in those without the hashtag, p<0.001). Conclusions: The use of the hashtag #ActuallyAutistic is associated with a different emotional tone, characterized by less joy and more sadness. These results suggest the need for greater support and acceptance towards the autistic community, both online and in society in general. Insights from our study can be valuable for policy makers, health, educational or other programmes aiming at enhancing well-being, inclusiveness, improve services, and create a more compassionate and understanding atmosphere for autistic people.
Item Type: |
Book Section (Book Chapter) |
|---|---|
Division/Institute: |
School of Engineering and Computer Science > Institute for Patient-centered Digital Health School of Engineering and Computer Science > Institute for Patient-centered Digital Health > AI for Health School of Engineering and Computer Science |
Name: |
Gabarron, Elia; Dorronzoro, Enrique; Rivera-Romero, Octavio; Denecke, Kerstin  0000-0001-6691-396X; Mantas, John; Hasman, Arie; Demiris, George; Saranto, Kaija; Marschollek, Michael; Arvanitis, Theodoros N.; Ognjanović, Ivana; Benis, Arriel; Gallos, Parisis; Zoulias, Emmanouil and Andrikopoulou, Elisavet |
Subjects: |
Q Science > Q Science (General) R Medicine > R Medicine (General) T Technology > T Technology (General) |
ISBN: |
9781643685335 |
Series: |
Studies in Health Technology and Informatics |
Publisher: |
IOS Press |
Language: |
English |
Submitter: |
Kerstin Denecke |
Date Deposited: |
11 Sep 2024 09:42 |
Last Modified: |
18 Sep 2024 10:23 |
Publisher DOI: |
10.3233/SHTI240804 |
ARBOR DOI: |
10.24451/arbor.22401 |
URI: |
https://arbor.bfh.ch/id/eprint/22401 |
Actions (login required)
 |
View Item |