Skip to main content Skip to navigation

Utilizing ChatGPT in a Data Structures and Algorithms Course: A Teaching Assistant's Perspective

Project Overview

The document explores the integration of generative AI, particularly ChatGPT, in educational settings, focusing on its application in data structures and algorithms (DSA) courses. By leveraging AI as a teaching assistant, the educational experience is enhanced through personalized support, which has been shown to significantly boost student engagement and performance—students using AI assistance scored an average of 16.50 points higher. This hybrid model effectively combines the expertise of human TAs with the capabilities of AI, providing reliable and innovative instructional support. However, the implementation of generative AI also raises concerns regarding potential over-reliance on technology and the integrity of academic work. Overall, the findings indicate that while generative AI can substantially improve learning outcomes, careful consideration is necessary to mitigate associated challenges.

Key Applications

ChatGPT as a supplementary tool for teaching assistants

Context: Data Structures and Algorithms course for undergraduate students

Implementation: TAs used ChatGPT guided by structured prompts to assist in answering student questions and creating exercises

Outcomes: Students in the ChatGPT-assisted group scored 16.50 points higher on average and excelled in advanced topics, demonstrating improved engagement and understanding.

Challenges: Limitations of ChatGPT included issues with generating creative problems, visual representation, and complex algorithmic reasoning, necessitating TA verification.

Implementation Barriers

Technical Limitations

ChatGPT struggled with generating creative exercises and providing accurate visual representations for complex algorithmic problems.

Proposed Solutions: Implementing human oversight to verify AI-generated answers and refining the prompts used to guide ChatGPT.

Academic Integrity

Potential for academic dishonesty and over-reliance on AI-generated content.

Proposed Solutions: Encouraging active engagement and critical thinking through structured prompts and TA verification.

Project Team

Pooriya Jamie

Researcher

Reyhaneh Hajihashemi

Researcher

Sharareh Alipour

Researcher

Contact Information

For information about the paper, please contact the authors.

Authors: Pooriya Jamie, Reyhaneh Hajihashemi, Sharareh Alipour

Source Publication: View Original PaperLink opens in a new window

Project Contact: Dr. Jianhua Yang

LLM Model Version: gpt-4o-mini-2024-07-18

Analysis Provider: Openai

Let us know you agree to cookies