Asee peer logo

Generative-AI Assisted Feedback Provisioning for Project-Based Learning in CS Courses

Download Paper |

Conference

2024 ASEE Annual Conference & Exposition

Location

Portland, Oregon

Publication Date

June 23, 2024

Start Date

June 23, 2024

End Date

July 12, 2024

Conference Session

Computing and Information Technology Division (CIT) Technical Session 3

Tagged Division

Computing and Information Technology Division (CIT)

Permanent URL

https://peer.asee.org/47494

Request a correction

Paper Authors

biography

Venkata Alekhya Kusam University of Michigan, Dearborn

visit author page

Venkata Alekhya Kusam is currently pursuing a Master's degree in Computer and Information Science at the University of Michigan-Dearborn. She has always been fascinated by the transformative power of technology. Her research interests lie in generative AI, large language models, and natural language processing (NLP).

visit author page

biography

Larnell Moore University of Michigan, Dearborn

visit author page

Larnell Moore is an undergraduate student in his final year pursuing a Bachelor's degree in Computer and Information Science at the University of Michigan-Dearborn. Alongside his studies, he has been working as a software engineer intern at the CSAA Insurance Group for a year. He has also worked as a supplemental instruction leader at the University of Michigan-Dearborn for two years. Larnell has been the recipient of numerous accolades such as the Rackham Merit Fellowship REA award, the title for the most exciting pitch at the 2023 CSAA Insurance Group Innovation Jam, the Destination Blue Scholarship, Slosberg and Sorscher Memorial Scholarship, CECS Richard Schaum Scholarship, funding for research under the NSF REU grant, and more. Post-graduation, Larnell Moore is set to pursue a Ph.D. in Computer Science and Engineering at the University of Michigan-Ann Arbor, aiming to further his research in Natural Language Processing, Deep Learning, and Machine Learning.

visit author page

biography

Summit Shrestha University of Michigan, Dearborn

visit author page

Summit Shrestha received his Bachelors of Science degree in Computer Science from Tribhuvan University in 2018. He is currently pursuing his Master's in Computer and Information Science at the University of Michigan-Dearborn, where he is also working as a Research Assistant with the Pervasive Computing Lab. Before joining the Master's program, he worked in software and systems as a Software Engineer, Lead Software Engineer, and then Principal Engineer with non-profit organizations and software companies overseas. His past experience working with educational and learning systems for K-12 education in rural Nepal has shaped his research focus on building system support for resource-constrained environments. His current research interests include edge computing and distributed systems, adaptive systems, middleware, sustainable and scalable edge systems, educational technologies and learning sciences.

visit author page

biography

Zheng Song University of Michigan, Dearborn

visit author page

Dr. Song received his second PhD in Computer Science (with a focus on distributed systems and software engineering) from Virginia Tech USA in 2020, and the first PhD (with a focus on wireless networking and mobile computing) from Beijing University of Posts and Telecommunications China in 2015. He worked as a software engineer at Sina for one year after I graduated as a master from China Agriculture University in 2009. He received the Best Paper Award from IEEE Edge in 2019.

visit author page

biography

Jin Lu University of Georgia

visit author page

Jin Lu received his Ph.D. degree in computer science and engineering from the University of Connecticut, USA in 2019. He worked as an assistant professor at the University of Michigan - Dearborn from 2019 to 2023. He is currently an assistant professor at the School of Computing at the University of Georgia. My major research interests include machine learning, data mining, and optimization. I am particularly interested in transparent machine learning models, distributed learning algorithms, optimization and so on.

visit author page

biography

Qiang Zhu University of Michigan, Dearborn

visit author page

Qiang Zhu received his Ph.D. degree in computer science from the University of Waterloo, Canada, in 1995. He is currently a Professor and the Chair of the Department of Computer and Information Science, University of Michigan - Dearborn, USA. He has been honored as the William E. Stirton Professor at his University, an ACM Distinguished Scientist, an IEEE Senior Member, and an IBM CAS Faculty Fellow. His current research interests include query optimization for advanced database systems, big data processing and analytics, streaming data processing, spatio-temporal data processing, data mining, federated learning, and data security and privacy.

visit author page

Download Paper |

Abstract

Project-Based Learning (PBL) is a pedagogical method that combines theory and practice by involving students in real-world challenges. Continuous feedback is crucial in PBL, guiding students to improve their methods and foster progressive thinking. However, PBL faces challenges in widespread adoption due to the time and expertise needed for effective feedback, especially with increasing student numbers. This paper presents a novel approach using Generative AI, specifically an enhanced ChatGPT, to provide effective PBL feedback. For an undergraduate Web Technology course, we integrated three strategies: 1) fine-tuning ChatGPT with feedback from various sources; 2) using additional course-specific information for context; 3) incorporating external services for specialized feedback. We developed a tool that implements these strategies both independently and in a combined fashion. We assessed the effectiveness of the tool we developed by conducting user studies, which confirmed that this tool improves the quality of feedback as compared with general-purpose ChatGPT. By acquiring and retaining knowledge from different sources, our approach offers a powerful component for implementing PBL on a large scale.

Kusam, V. A., & Moore, L., & Shrestha, S., & Song, Z., & Lu, J., & Zhu, Q. (2024, June), Generative-AI Assisted Feedback Provisioning for Project-Based Learning in CS Courses Paper presented at 2024 ASEE Annual Conference & Exposition, Portland, Oregon. https://peer.asee.org/47494

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2024 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015