NotesFAQContact Us
Collection
Advanced
Search Tips
Back to results
Peer reviewed Peer reviewed
PDF on ERIC Download full text
ERIC Number: EJ1462116
Record Type: Journal
Publication Date: 2025
Pages: 19
Abstractor: As Provided
ISBN: N/A
ISSN: N/A
EISSN: EISSN-1545-679X
Available Date: 0000-00-00
A Comparison of Generative AI Solutions and Textbook Solutions in an Introductory Programming Course
Ernst Bekkering; Patrick Harrington
Information Systems Education Journal, v23 n1 p4-22 2025
Generative AI has recently gained the ability to generate computer code. This development is bound to affect how computer programming is taught in higher education. We used past programming assignments and solutions for textbook exercises in our introductory programming class to analyze how accurately one of the leading models, ChatGPT, generates solutions. We selected the ChatGPT-4 available through the Bing search engine for our testing. We used a one-tailed test to calculate success percentage of the textbook versus ChatGPT solutions to determine if there was a statistically significant difference. Neither the book nor ChatGPT provided perfect solutions. Analysis of the results showed that the generated code does not always meet the programming requirements, but also that instructions for generative AI coding and for traditional programming can be improved. We conclude with recommendations for incorporating generative AI in programming classes. [Note: The publication year (2024) shown in the citation on the PDF is incorrect. The correct publication year is 2025.]
Information Systems and Computing Academic Professionals. Box 488, Wrightsville Beach, NC 28480. e-mail: publisher@isedj.org; Web site: http://isedj.org
Publication Type: Journal Articles; Reports - Research
Education Level: Higher Education; Postsecondary Education
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: N/A
Grant or Contract Numbers: N/A
Author Affiliations: N/A