2021/08/30 by Jacob Beel, Beel, Jacob, Tong Xiang +5
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Hate Speech and Cyberbullying Detection #Sentiment Analysis and Opinion Mining #Social and Information Networks (cs.SI) #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2108.13556
openalex publication_date 2021/08/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
As public discourse continues to move and grow online, conversations about divisive topics on social media platforms have also increased. These divisive topics prompt both contentious and non-contentious conversations. Although what distinguishes these conversations, often framed as what makes these conversations contentious, is known in broad strokes, much less is known about the linguistic signature of these conversations. Prior work has shown that contentious content and structure can be a predictor for this task, however, most of them have been focused on conversation in general, very specific events, or complex structural analysis. Additionally, many models used in prior work have lacked interpret-ability, a key factor in online moderation. Our work fills these gaps by focusing on conversations from highly divisive topics (abortion, climate change, and gun control), operationalizing a set of novel linguistic and conversational characteristics and user factors, and incorporating them to build interpretable models. We demonstrate that such characteristics can largely improve the performance of prediction on this task, and also enable nuanced interpretability. Our case studies on these three contentious topics suggest that certain generic linguistic characteristics are highly correlated with contentiousness in conversations while others demonstrate significant contextual influences on specific divisive topics.