Iris: An AI-Driven Virtual Tutor For Computer Science Education

被引:17
作者
Bassner, Patrick [1 ]
Frankford, Eduard [2 ]
Krusche, Stephan [1 ]
机构
[1] Tech Univ Munich, Munich, Germany
[2] Univ Innsbruck, Innsbruck, Austria
来源
PROCEEDINGS OF THE 2024 CONFERENCE INNOVATION AND TECHNOLOGY IN COMPUTER SCIENCE EDUCATION, VOL 1, ITICSE 2024 | 2024年
关键词
Generative AI; ChatGPT; Large Language Models; Interactive Learning; Education Technology; Programming Exercises; CS1;
D O I
10.1145/3649217.3653543
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Integrating AI-driven tools in higher education is an emerging area with transformative potential. This paper introduces Iris, a chat-based virtual tutor integrated into the interactive learning platform Artemis that offers personalized, context-aware assistance in large-scale educational settings. Iris supports computer science students by guiding them through programming exercises and is designed to act as a tutor in a didactically meaningful way. Its calibrated assistance avoids revealing complete solutions, offering subtle hints or counter-questions to foster independent problem-solving skills. For each question, it issues multiple prompts in a Chain-of-Thought to GPT-3.5-Turbo. The prompts include a tutor role description and examples of meaningful answers through few-shot learning. Iris employs contextual awareness by accessing the problem statement, student code, and automated feedback to provide tailored advice. An empirical evaluation shows that students perceive Iris as effective because it understands their questions, provides relevant support, and contributes to the learning process. While students consider Iris a valuable tool for programming exercises and homework, they also feel confident solving programming tasks in computer-based exams without Iris. The findings underscore students' appreciation for Iris' immediate and personalized support, though students predominantly view it as a complement to, rather than a replacement for, human tutors. Nevertheless, Iris creates a space for students to ask questions without being judged by others.
引用
收藏
页码:394 / 400
页数:7
相关论文
共 33 条
[1]  
Ali F, 2023, Learning Research and Practice, V9, P135, DOI [10.1080/23735082.2023.2258886, 10.1080/23735082.2023.2258886, DOI 10.1080/23735082.2023.2258886]
[2]   Programming Is Hard - Or at Least It Used to Be: Educational Opportunities and Challenges of AI Code Generation [J].
Becker, Brett A. ;
Denny, Paul ;
Finnie-Ansley, James ;
Luxton-Reilly, Andrew ;
Prather, James ;
Santos, Eddie Antonio .
PROCEEDINGS OF THE 54TH ACM TECHNICAL SYMPOSIUM ON COMPUTER SCIENCE EDUCATION, VOL 1, SIGCSE 2023, 2023, :500-506
[3]  
Brown TB, 2020, ADV NEUR IN, V33
[4]  
Cao CC, 2023, Arxiv, DOI [arXiv:2308.03992, 10.48550/arXiv.2308.03992, DOI 10.48550/ARXIV.2308.03992]
[5]   Artificial Intelligence (AI) Student Assistants in the Classroom: Designing Chatbots to Support Student Success [J].
Chen, Yu ;
Jensen, Scott ;
Albert, Leslie J. ;
Gupta, Sambhav ;
Lee, Terri .
INFORMATION SYSTEMS FRONTIERS, 2023, 25 (01) :161-182
[6]   To Elicit Or To Tell: Does It Matter? [J].
Chi, Min ;
Jordan, Pamela ;
Vanlehn, Kurt ;
Litman, Diane .
ARTIFICIAL INTELLIGENCE IN EDUCATION: BUILDING LEARNING SYSTEMS THAT CARE: FROM KNOWLEDGE REPRESENTATION TO AFFECTIVE MODELLING, 2009, 200 :197-+
[7]  
Crow T., 2018, Proceedings of the 20th Australasian Computing Education Conference, Brisbane, Queensland, Australia, ACM, P53, DOI [10.1145/3160489.3160492, DOI 10.1145/3160489.3160492]
[8]   Chatbot in a Campus Environment: Design of LiSA, a Virtual Assistant to Help Students in Their University Life [J].
Dibitonto, Massimiliano ;
Leszczynska, Katarzyna ;
Tazzi, Federica ;
Medaglia, Carlo M. .
HUMAN-COMPUTER INTERACTION: INTERACTION TECHNOLOGIES, HCI INTERNATIONAL 2018, PT III, 2018, 10903 :103-116
[9]  
Frankford Eduard, 2024, 46 INT C SOFTW ENG S
[10]   Chatbot learning partners: Connecting learning experiences, interest and competence [J].
Fryer, Luke K. ;
Nakao, Kaori ;
Thompson, Andrew .
COMPUTERS IN HUMAN BEHAVIOR, 2019, 93 :279-289