Generation and Evaluation of a Culturally-Relevant CS1 Textbook for Latines using Large Language Models
Open Access
- 3 July 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 325-331
Abstract
In the United States, culturally relevant computing (CRC) is one of the most popular pedagogical implementations for Latin American (Latine) students. Culturally-relevant learning resources are a valuable tool for implementing CRC. However, the traditional method of creation and maintenance of textbooks takes a significant amount of time and effort. Given the duration required for textbook production, the development of culturally-relevant learning resources may become lengthened, as it requires close attention both on the material and the incorporation of cultural referents. In order to accelerate the process, we used the advancement of large language models (LLMs) to our advantage. Through prompt engineering, we created a series of prompts to produce a textbook for an introductory computer science course (CS1) that incorporates Latine culture. This textbook was evaluated on metrics regarding sensibility, correctness, readability, linguistic approachability, appropriateness of examples, and cultural relevance. Overall, the generated textbook was mainly sensible, correct, readable, and linguistically approachable. Code examples were not always appropriate due to the usage of libraries that are not typically used in a CS1 course. The cultural relevance was apparent, but it often included surface-level cultural referents. The main incorporation of culture was through geographical locations and people's names. This suggests that the use of LLMs to generate textbooks may serve as a valuable first step for writing culturally-relevant learning resources. Though this study focuses on Latines, our results and prompts may be applicable for generating culturally-relevant CS1 textbooks for other cultures.Keywords
This publication has 31 references indexed in Scilit:
- Perception, performance, and detectability of conversational artificial intelligence across 32 university coursesScientific Reports, 2023
- ChatGPT for good? On opportunities and challenges of large language models for educationLearning and Individual Differences, 2023
- Learning about the Experiences of Chicano/Latino Students in a Large Undergraduate CS Program2022
- “What Happens to the Raspado man in a Cash-free Society?”: Teaching and Learning Socially Responsible ComputingACM Transactions on Computing Education, 2021
- Exploration of Intersectionality and Computer Science DemographicsACM Transactions on Computing Education, 2021
- The Role of Translanguaging in Computational Literacies2019
- Sol y Agua: A Game-based Learning Platform to Engage Middle-school Students in STEM2018
- Animal tlatoque2011
- Engaging constructions2008
- But that's just good teaching! The case for culturally relevant pedagogyTheory Into Practice, 1995