Date of Award

5-30-2026

Document Type

Thesis

Publisher

Santa Clara : Santa Clara University, 2026

Department

Computer Science and Engineering

First Advisor

Sean Choi

Abstract

Developing public-speaking skills remains a persistent challenge in formal education, constrained by limited instructional time and the lack of scalable, individualized feedback. Existing automated tools address only narrow aspects of this problem, offering text-based coaching against rigid rubrics that fail to capture argument quality, evidence use, or real-time rebuttal skill. This thesis presents Debatrix, an AI-powered platform that enables K-12 students, university learners, and independent self-studiers to debate an intelligent opponent. The system combines automatic speech recognition, large language model-driven rebuttal generation, and a multi-dimensional rhetorical analysis engine that evaluates argument structure, evidence integration, and persuasive technique. Users receive explainable scores and targeted feedback after each session. Evaluation of the argument scoring component demonstrates our debate agent scored on average 62.5 percent, with our highest performing model, DeepSeek R1, scoring at 78 percent. These contributions establish a foundation for scalable, accessible debate training that reduces reliance on instructormediated practice.

Download

Share

COinS