2026-09-23T22:42:27Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/125603 2025-02-06 col_2142_5131 col_2142_10761 com_2142_5130 com_2142_10755 com_2142_234

application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-02-04 without embargo terms The student, Ridha Alkhabaz, accepted the attached license on 2024-07-10 at 05:28. The student, Ridha Alkhabaz, submitted this Thesis for approval on 2024-07-10 at 05:50. This Thesis was approved for publication on 2024-07-16 at 15:39. DSpace SAF Submission Ingestion Package generated from Vireo submission #21035 on 2025-02-04 at 21:04:51 Online conversations: A study of their toxicity Alkhabaz, Ridha Monir A. 2024-07-16 Sundaram, Hari Toxicity Online Conversations Graph Neural Networks Turn-taking Paths Terminating Conversational Structures Network Science eng Social media platforms are essential spaces for modern human communication. There is a dire need to make these spaces most welcoming and engaging to their participants. A potential threat to this need is the propagation of toxic content in online spaces. Hence, it becomes crucial for social media platforms to detect early signs of a toxic conversation. In this work, we tackle the problem of toxicity prediction by proposing a definition for conversational structures. This definition empowers us to provide a new framework for toxicity prediction. Thus, we examine more than 1.18 million X (made by 4.4 million users), formerly known as Twitter, threads to provide a few key insights about the current state of online conversations. Our results indicated that most of the X threads do not exhibit a conversational structure. Also, our newly defined structures are distributed differently than previously thought of online conversations. Additionally, our definitions give a meaningful sign for models to start predicting the future toxicity of online conversations. We also showcase that message-passing graph neural networks outperform state-of-the-art gradient-boosting trees for toxicity prediction. Most importantly, we find that once we observe the first two terminating conversational structures, we can predict the future toxicity of online thread with ≈ 88 % accuracy. We hope our findings will help social media platforms better curate content in their spaces and promote more conversations in online spaces. 2024-08 Thesis https://hdl.handle.net/2142/125603 Copyright 2024 Ridha Alkhabaz Siebel Computing &DataScience Computer Science University of Illinois at Urbana-Champaign M.S. Thesis