IEEE VIS 2024 Content: StuGPTViz: A Visual Analytics Approach to Understand Student-ChatGPT Interactions

StuGPTViz: A Visual Analytics Approach to Understand Student-ChatGPT Interactions

Zixin Chen - The Hong Kong University of Science and Technology, Hong Kong, China

Jiachen Wang - The Hong Kong University of Science and Technology, Sai Kung, China

Meng Xia - Texas A. M University, College Station, United States

Kento Shigyo - The Hong Kong University of Science and Technology, Kowloon, Hong Kong

Dingdong Liu - The Hong Kong University of Science and Technology, Hong Kong, China

Rong Zhang - Hong Kong University of Science and Technology, Hong Kong, Hong Kong

Huamin Qu - The Hong Kong University of Science and Technology, Hong Kong, China

Screen-reader Accessible PDF

Room: Bayshore V

2024-10-16T16:00:00ZGMT-0600Change your timezone on the schedule page
2024-10-16T16:00:00Z
Exemplar figure, described by caption below
We developed StuGPTViz, a visual analytics system designed to analyze and compare student interactions with ChatGPT in a master's-level data visualization course. By categorizing prompts and responses using a coding scheme grounded in literature on cognitive levels and thematic analysis, the system reveals key patterns and insights. Validated through expert interviews and case studies, StuGPTViz enhances educators' understanding of ChatGPT's pedagogical value, demonstrating the potential of visual analytics to drive AI-driven personalized learning and improve educational outcomes.
Fast forward
Keywords

Visual analytics for education, ChatGPT for education, student-ChatGPT interaction

Abstract

The integration of Large Language Models (LLMs), especially ChatGPT, into education is poised to revolutionize students’ learning experiences by introducing innovative conversational learning methodologies. To empower students to fully leverage the capabilities of ChatGPT in educational scenarios, understanding students’ interaction patterns with ChatGPT is crucial for instructors. However, this endeavor is challenging due to the absence of datasets focused on student-ChatGPT conversations and the complexities in identifying and analyzing the evolutional interaction patterns within conversations. To address these challenges, we collected conversational data from 48 students interacting with ChatGPT in a master’s level data visualization course over one semester. We then developed a coding scheme, grounded in the literature on cognitive levels and thematic analysis, to categorize students’ interaction patterns with ChatGPT. Furthermore, we present a visual analytics system, StuGPTViz, that tracks and compares temporal patterns in student prompts and the quality of ChatGPT’s responses at multiple scales, revealing significant pedagogical insights for instructors. We validated the system’s effectiveness through expert interviews with six data visualization instructors and three case studies. The results confirmed StuGPTViz’s capacity to enhance educators’ insights into the pedagogical value of ChatGPT. We also discussed the potential research opportunities of applying visual analytics in education and developing AI-driven personalized learning solutions.