Customizing ChatGPT to Help Computer Science Principles Students Learn Through Conversation
Abstract
This paper explores leveraging conversational agents, specifically ChatGPT, to enhance the introduction of computing, focused on the Advanced Placement Computer Science Principles (CSP) course in secondary schools. Despite the potential benefits for diverse student audiences, little research has investigated their effectiveness and engagement in this context. We examine the customization of ChatGPT for secondary school CSP students, assessing its impact on exploratory searches for learning CSP concepts. Results from 20 high school students in grades 10-12 (ages 15-18) in a CSP course indicate that students preferred a customized ChatGPT, with its terminology more suitable to secondary school level, examples more understandable, and better connections to personal experiences compared to standard ChatGPT.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A second major objective is to situate the development of computational thinking and programming competence within authentic practices, using AI-powered programming environments and intelligent feedback mechanisms to lower entry barriers, provide personalized guidance, and ensure timely feedback for novice learners.
“A second major objective is to situate the development of computational thinking and programming competence within authentic practices. Here, the target is to support students in refining their algorithmic reasoning, problem decomposition, and coding practices. The integration of AI-powered programming environments and intelligent feedback mechanisms serves to meet these goals, particularly by low”
From A Systematic Review of Generative AI in K–12: Mapping Goals, Activities, Roles, and Outcomes via the 3P Model (2025) · cites this paper as [97]
GenAI serves as a cognitive scaffold by collecting student input in real time, adaptively modifying examples and prompts, and integrating support functions such as simplified language, summarization, and length control within the same workspace.
“First, GenAI serves as a cognitive scaffold. By leveraging conversational interfaces, the system collects student input in real time, adaptively modifies examples and prompts, and integrates support functions such as simplified language, summarization, and length control within the same workspace.”
From A Systematic Review of Generative AI in K–12: Mapping Goals, Activities, Roles, and Outcomes via the 3P Model (2025) · cites this paper as [97]
Teacher presence and guidance, together with personalization in AI tool design, are key enabling conditions.
“Teacher presence and guidance [82,107], together with personalization in AI tool design [97], are key enabling conditions.”
From A Systematic Review of Generative AI in K–12: Mapping Goals, Activities, Roles, and Outcomes via the 3P Model (2025) · cites this paper as [97]
Cites
Scaling Laws for Neural Language Models
Kaplan, J., McCandlish, S., Henighan, T., Brown, T. B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., & Amodei, D. (2020) · arXiv · Cited by 1,749 · cited 1× · see citing works
“Prompt engineering techniques such as zero-shot (directing the model without prior examples) [43] and few-shot (providing a limited number of examples) [22, 41] are widely utilized.”
Exploratory search: from finding to understanding
Marchionini, G. (2006) · Communications of the ACM · doi:10.1145/1121949.1121979 · Cited by 1,506 · see citing works
Expanding computer science education in schools: understanding teacher experiences and challenges
Yadav, A., Gretter, S., Hambrusch, S. E., et al. (2016) · Computer Science Education · doi:10.1080/08993408.2016.1257418 · Cited by 308 · see citing works
Denny, P., Kumar, V., & Giacaman, N. (2023) · Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1 · doi:10.1145/3545945.3569823 · Cited by 287 · see citing works
Winkler, R., Hobert, S., Salovaara, A., Söllner, M., & Leimeister, J. M. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376781 · Cited by 177 · see citing works
Athukorala, K., Głowacka, D., Jacucci, G., Oulasvirta, A., & Vreeken, J. (2016) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.23617 · Cited by 150 · see citing works
Generative AI in Computing Education: Perspectives of Students and Instructors
Zastudil, C., Rogalska, M., Kapp, C., Vaughn, J., & MacNeil, S. (2023) · 2023 IEEE Frontiers in Education Conference (FIE) · doi:10.1109/fie58773.2023.10343467 · Cited by 136 · see citing works
Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors
Phung, T., Pădurean, V.-A., Cambronero, J., Gulwani, S., Kohn, T., Majumdar, R., Singla, A., & Soares, G. (2023) · Proceedings of the 2023 ACM Conference on International Computing Education Research - Volume 2 · doi:10.1145/3568812.3603476 · Cited by 112 · see citing works
Bull, C., & Kharrufa, A. (2024) · IEEE Software · doi:10.1109/ms.2023.3300574 · Cited by 82 · see citing works
Creative Use of OpenAI in Education: Case Studies from Game Development
French, F., Levi, D., Maczo, C., Simonaityte, A., Triantafyllidis, S., & Varda, G. (2023) · Multimodal Technologies and Interaction · doi:10.3390/mti7080081 · Cited by 64 · see citing works
Nudging the Classroom: Designing a Socio-Technical Artifact to Reduce Academic Procrastination
Rodriguez, J., Piccoli, G., & Bartosiak, M. (2019) · Hawaii International Conference on System Sciences (HICSS) · doi:10.24251/hicss.2019.533 · Cited by 34 · see citing works
EDUBOT-A Chatbot For Education in Covid-19 Pandemic and VQAbot Comparison
Sophia, J. J., & Jacob, T. P. (2021) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc51422.2021.9532611 · Cited by 31 · see citing works
Shein, E. (2019) · Communications of the ACM · doi:10.1145/3355375 · Cited by 28 · see citing works
AI-Generated Code Not Considered Harmful
Kendon, T., Wu, L., & Aycock, J. (2023) · Proceedings of the 25th Western Canadian Conference on Computing Education · doi:10.1145/3593342.3593349 · Cited by 13 · see citing works
An Adaptive Tutor to Promote Learners' Skills Acquisition during Procedural Learning
Taoum, J., Raison, A., Bevcqua, E., & Querrec, R. (2018) · HAL · Cited by 4 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Lin, X., & Tan, H. (2025) · Systems · doi:10.3390/systems13100840 · Cited by 22 · see citing works
- Authors
- Frazier, M., Damevski, K., & Pollock, L.
- Affiliations
- University of Delaware (US)
- Virginia Commonwealth University (US)
- Venue
- Proceedings of the 2024 on Innovation and Technology in Computer Science Education V. 1
- Publisher
- ACM
- Published
- 2024-07-03
- Pages
- 633-639
- OpenAlex
- W4400267766
- Cited by
- 2
- References
- 15
- Citations by year
- 2025: 2
- FWCI
- 0.88
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM Conference on Innovation and Technology in Computer Science Education (ITiCSE) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Science Applications › Teaching and Learning Programming
- Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Keywords
- ChatGPT, chatbots, computer science education, high school students, student engagement, exploratory learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
