Paper Type
Complete
Description
The surge in toxic content on social media platforms has raised concerns about its impact on public discourse. This research explores toxicity within X (formerly, Twitter) discussions, leveraging epidemiological models—SIR, SIS, and STRS—traditionally used for infectious disease dynamics. Previous studies have not examined the level and intensity of toxicity in propagation; this study seeks to uncover the patterns of toxicity spreading in social media. The results highlight the STRS model's superior performance in capturing toxicity diffusion dynamics across diverse datasets. The study indicates that in COVID-related datasets, moderate toxicity users show better conformance to the STRS model, indicating a more dynamic engagement. Conversely, in social movement datasets, high toxicity users exhibit greater compliance with the STRS model with lower error rate. The study identifies dynamic population groups that follow the model in a more consistent manner, guiding policymakers in creating effective interventions to prevent toxicity.
Paper Number
1509
Recommended Citation
Yousefi, Niloofar and Agarwal, Nitin, "Study the Influence of Toxicity Intensity on Its Propagation Using Epidemiological Models" (2024). AMCIS 2024 Proceedings. 17.
https://aisel.aisnet.org/amcis2024/social_comp/social_comput/17
Study the Influence of Toxicity Intensity on Its Propagation Using Epidemiological Models
The surge in toxic content on social media platforms has raised concerns about its impact on public discourse. This research explores toxicity within X (formerly, Twitter) discussions, leveraging epidemiological models—SIR, SIS, and STRS—traditionally used for infectious disease dynamics. Previous studies have not examined the level and intensity of toxicity in propagation; this study seeks to uncover the patterns of toxicity spreading in social media. The results highlight the STRS model's superior performance in capturing toxicity diffusion dynamics across diverse datasets. The study indicates that in COVID-related datasets, moderate toxicity users show better conformance to the STRS model, indicating a more dynamic engagement. Conversely, in social movement datasets, high toxicity users exhibit greater compliance with the STRS model with lower error rate. The study identifies dynamic population groups that follow the model in a more consistent manner, guiding policymakers in creating effective interventions to prevent toxicity.
Comments
SOCCOMP