Scaling CS1 Support with Compiler-Integrated Conversational AI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Renzella, Jake, Vassar, Alexandra, Solano, Lorenzo Lee, Taylor, Andrew
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916346590134272
author Renzella, Jake
Vassar, Alexandra
Solano, Lorenzo Lee
Taylor, Andrew
author_facet Renzella, Jake
Vassar, Alexandra
Solano, Lorenzo Lee
Taylor, Andrew
contents This paper introduces DCC Sidekick, a web-based conversational AI tool that enhances an existing LLM-powered C/C++ compiler by generating educational programming error explanations. The tool seamlessly combines code display, compile- and run-time error messages, and stack frame read-outs alongside an AI interface, leveraging compiler error context for improved explanations. We analyse usage data from a large Australian CS1 course, where 959 students engaged in 11,222 DCC Sidekick sessions, resulting in 17,982 error explanations over seven weeks. Notably, over 50% of interactions occurred outside business hours, underscoring the tool's value as an always-available resource. Our findings reveal strong adoption of AI-assisted debugging tools, demonstrating their scalability in supporting extensive CS1 courses. We provide implementation insights and recommendations for educators seeking to incorporate AI tools with appropriate pedagogical safeguards.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02378
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scaling CS1 Support with Compiler-Integrated Conversational AI
Renzella, Jake
Vassar, Alexandra
Solano, Lorenzo Lee
Taylor, Andrew
Computers and Society
Artificial Intelligence
Software Engineering
This paper introduces DCC Sidekick, a web-based conversational AI tool that enhances an existing LLM-powered C/C++ compiler by generating educational programming error explanations. The tool seamlessly combines code display, compile- and run-time error messages, and stack frame read-outs alongside an AI interface, leveraging compiler error context for improved explanations. We analyse usage data from a large Australian CS1 course, where 959 students engaged in 11,222 DCC Sidekick sessions, resulting in 17,982 error explanations over seven weeks. Notably, over 50% of interactions occurred outside business hours, underscoring the tool's value as an always-available resource. Our findings reveal strong adoption of AI-assisted debugging tools, demonstrating their scalability in supporting extensive CS1 courses. We provide implementation insights and recommendations for educators seeking to incorporate AI tools with appropriate pedagogical safeguards.
title Scaling CS1 Support with Compiler-Integrated Conversational AI
topic Computers and Society
Artificial Intelligence
Software Engineering
url https://arxiv.org/abs/2408.02378