Conch: Competitive Debate Analysis via Visualizing Clash Points and Hierarchical Strategies
🤖 AI Summary
Unstructured textual records of competitive debate lack explicit annotations, impeding contextual reconstruction and logical chain tracing, and resulting in low-efficiency manual analysis. To address this, we propose a novel approach integrating large language models (LLMs) with parallel spiral visualization. First, prompt engineering guides the LLM to automatically extract key semantic elements—including claims, disagreements, and argumentation strategies. Second, we design a compact parallel spiral diagram to encode multidimensional temporal evolution and inter-participant interactions of conflict points. Third, we implement an interactive visualization system supporting debate topic focus mining and strategic progression analysis. Case studies and user experiments on real-world debate datasets demonstrate that our method significantly improves analytical efficiency—reducing average analysis time by 62%—and enhances interpretability and conceptual depth. The framework provides explainable, actionable technical support for debate training, pedagogy, and evaluation.
Application Category
📝 Abstract
In-depth analysis of competitive debates is essential for participants to develop argumentative skills and refine strategies, and further improve their debating performance. However, manual analysis of unstructured and unlabeled textual records of debating is time-consuming and ineffective, as it is challenging to reconstruct contextual semantics and track logical connections from raw data. To address this, we propose Conch, an interactive visualization system that systematically analyzes both what is debated and how it is debated. In particular, we propose a novel parallel spiral visualization that compactly traces the multidimensional evolution of clash points and participant interactions throughout debate process. In addition, we leverage large language models with well-designed prompts to automatically identify critical debate elements such as clash points, disagreements, viewpoints, and strategies, enabling participants to understand the debate context comprehensively. Finally, through two case studies on real-world debates and a carefully-designed user study, we demonstrate Conch's effectiveness and usability for competitive debate analysis.
Problem
Research questions and friction points this paper is trying to address.
Analyzing unstructured debate texts is time-consuming and ineffective
Reconstructing contextual semantics from raw debate data is challenging
Tracking logical connections in debates manually is difficult
Innovation
Methods, ideas, or system contributions that make the work stand out.
Parallel spiral visualization for debate evolution
LLMs identify debate elements automatically
Interactive system analyzes what and how debated
🔎 Similar Papers
No similar papers found.
