How Far Are We? The Triumphs and Trials of Generative AI in Learning Software Engineering

ACM/IEEE 46th International Conference on Software Engineering (ICSE 2024) Conversational Generative AI (convo-genAI) is revolutionizing Software Engineering (SE) as engineers and academics embrace this technology in their work. However, there is a gap in understanding the current potential and pitf...

Full description

Saved in:
Bibliographic Details
Main Authors Choudhuri, Rudrajit, Liu, Dylan, Steinmacher, Igor, Gerosa, Marco, Sarma, Anita
Format Journal Article
LanguageEnglish
Published 18.12.2023
Subjects
Computer Science - Human-Computer Interaction
Computer Science - Software Engineering
Online AccessGet full text
DOI10.48550/arxiv.2312.11719

Cover

More Information
Summary:ACM/IEEE 46th International Conference on Software Engineering (ICSE 2024) Conversational Generative AI (convo-genAI) is revolutionizing Software Engineering (SE) as engineers and academics embrace this technology in their work. However, there is a gap in understanding the current potential and pitfalls of this technology, specifically in supporting students in SE tasks. In this work, we evaluate through a between-subjects study (N=22) the effectiveness of ChatGPT, a convo-genAI platform, in assisting students in SE tasks. Our study did not find statistical differences in participants' productivity or self-efficacy when using ChatGPT as compared to traditional resources, but we found significantly increased frustration levels. Our study also revealed 5 distinct faults arising from violations of Human-AI interaction guidelines, which led to 7 different (negative) consequences on participants.
DOI:10.48550/arxiv.2312.11719