ABSTRACT
The power of large language models has opened up opportunities for educational use. In computing education, recent studies have demonstrated the potential of these models to improve learning and teaching experiences in university-level programming courses. However, research into leveraging them to aid computer science instructors in curriculum development and course material design is relatively sparse, especially at the K-12 level. This work aims to fill this gap by exploring the capability of large language models in ideating and designing culturally responsive projects for elementary and middle school programming classes. Our ultimate goal is to support K-8 teachers in effectively extracting suggestions from large language models by only using natural language modifications. Furthermore, we aim to develop a comprehensive assessment framework for culturally responsive AI-generated project ideas. We also hope to provide valuable insight into teachers’ perspectives on large language models and their integration into teaching practices.
Supplemental Material
- Kara Beason, James B Fenwick Jr, and Cindy Norris. 2020. Introducing middle school students to computational thinking with the CS first curriculum. In Proceedings of the 2020 ACM Southeast Conference. 10–17.Google ScholarDigital Library
- Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877–1901.Google Scholar
- Paul Denny, Viraj Kumar, and Nasser Giacaman. 2023. Conversing with Copilot: Exploring prompt engineering for solving CS1 problems using natural language. In Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1. 1136–1142.Google ScholarDigital Library
- Ron Eglash, Juan E Gilbert, and Ellen Foster. 2013. Toward culturally responsive computing education. Commun. ACM 56, 7 (2013), 33–36.Google ScholarDigital Library
- Diana Franklin, David Weintrop, Jennifer Palmer, Merijke Coenraad, Melissa Cobian, Kristan Beck, Andrew Rasmussen, Sue Krause, Max White, Marco Anaya, 2020. Scratch Encore: The design and pilot of a culturally-relevant intermediate Scratch curriculum. In Proceedings of the 51st ACM technical symposium on computer science education. 794–800.Google ScholarDigital Library
- Geneva Gay. 2018. Culturally responsive teaching: Theory, research, and practice. teachers college press.Google Scholar
- Filiz Kalelioğlu. 2015. A new way of teaching programming skills to K-12 students: Code. org. Computers in Human Behavior 52 (2015), 200–210.Google ScholarDigital Library
- Juho Leinonen, Arto Hellas, Sami Sarsa, Brent Reeves, Paul Denny, James Prather, and Brett A Becker. 2023. Using large language models to enhance programming error messages. In Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1. 563–569.Google ScholarDigital Library
- Stephen MacNeil, Andrew Tran, Arto Hellas, Joanne Kim, Sami Sarsa, Paul Denny, Seth Bernstein, and Juho Leinonen. 2023. Experiences from using code explanations generated by large language models in a web software development e-book. In Proceedings of the 54th ACM Technical Symposium on Computer Science Education V. 1. 931–937.Google ScholarDigital Library
- OpenAI. 2023. Introducing ChatGPT. https://openai.com/blog/chatgptGoogle Scholar
- Mitchel Resnick, John Maloney, Andrés Monroy-Hernández, Natalie Rusk, Evelyn Eastmond, Karen Brennan, Amon Millner, Eric Rosenbaum, Jay Silver, Brian Silverman, 2009. Scratch: programming for all. Commun. ACM 52, 11 (2009), 60–67.Google ScholarDigital Library
- Sami Sarsa, Paul Denny, Arto Hellas, and Juho Leinonen. 2022. Automatic generation of programming exercises and code explanations using large language models. In Proceedings of the 2022 ACM Conference on International Computing Education Research-Volume 1. 27–43.Google ScholarDigital Library
- Kimberly A Scott, Kimberly M Sheridan, and Kevin Clark. 2015. Culturally responsive computing: A theory revisited. Learning, Media and Technology 40, 4 (2015), 412–436.Google ScholarCross Ref
- Priyan Vaithilingam, Tianyi Zhang, and Elena L Glassman. 2022. Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models. In Chi conference on human factors in computing systems extended abstracts. 1–7.Google ScholarDigital Library
- JD Zamfirescu-Pereira, Richmond Y Wong, Bjoern Hartmann, and Qian Yang. 2023. Why Johnny can’t prompt: how non-AI experts try (and fail) to design LLM prompts. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. 1–21.Google ScholarDigital Library
Index Terms
- Prompt Engineering for Large Language Models to Support K-8 Computer Science Teachers in Creating Culturally Responsive Projects
Recommendations
Equipping Middle School Teachers with Culturally Responsive Pedagogy for Computer Science Through Community-centered Professional Development
SIGCSE 2022: Proceedings of the 53rd ACM Technical Symposium on Computer Science Education V. 2Culturally responsive pedagogy (CRP) has gained prominence in computer science education since it can effectively reach traditionally marginalized populations, which has led to new efforts toward broadening participation in computer science (CS). The CS ...
Equipping Middle School Teachers with Culturally Responsive Pedagogy in Teaching Computer Science Through Professional Learning
ICER '23: Proceedings of the 2023 ACM Conference on International Computing Education Research - Volume 2Culturally responsive pedagogy (CRP) has gained prominence in computer science (CS) education since it can effectively reach traditionally marginalized populations. Teacher professional development has been found to be the most effective way to enhance ...
Comments