Iris: An AI-Driven Virtual Tutor For Computer Science Education
Project Overview
The document explores the use of Iris, an AI-driven virtual tutor integrated into the Artemis learning platform, aimed at improving computer science education. By delivering personalized and context-aware support through a chat interface, Iris assists students with programming exercises by providing hints rather than direct answers, thereby promoting independent problem-solving skills. Evaluations indicate that students find Iris effective and valuable, although they consider it a supplementary resource rather than a substitute for human tutors. The findings underscore the potential of generative AI to enhance personalized learning experiences in large educational environments, while also highlighting concerns regarding over-reliance on AI tools. Overall, the implementation of Iris illustrates the growing role of generative AI in education and its impact on teaching and learning dynamics.
Key Applications
Iris, an AI-driven virtual tutor integrated into the Artemis platform
Context: Higher education, specifically aimed at computer science students in large courses (over 1,000 students)
Implementation: Iris integrates with the Artemis platform to provide context-aware assistance and utilizes a chat interface for personalized interactions.
Outcomes: Students report that Iris understands their questions and provides relevant support, improving their understanding of programming concepts and engagement in learning.
Challenges: Some students prefer human tutors for complex questions and may not fully rely on Iris for exam preparation.
Implementation Barriers
Technical Barrier
General-purpose AI tools like ChatGPT typically require students to provide exercise details manually, which can be time-consuming and challenging. Iris offers context-aware assistance by integrating exercise problem statements and student code, reducing the cognitive load on students.
Proposed Solutions: Implement Iris to streamline the process for students by automatically integrating relevant information.
Perception Barrier
Students may feel more comfortable asking human tutors questions instead of relying solely on an AI tutor. It is important to promote the use of Iris as a complementary tool and ensure students understand its role in their learning process.
Proposed Solutions: Provide training and support to help students see the value of AI in their education.
Project Team
Patrick Bassner
Researcher
Eduard Frankford
Researcher
Stephan Krusche
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Patrick Bassner, Eduard Frankford, Stephan Krusche
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