arXiv Open Access 2023

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

Rudrajit Choudhuri Dylan Liu Igor Steinmacher Marco Gerosa Anita Sarma
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

Penulis (5)

R

Rudrajit Choudhuri

D

Dylan Liu

I

Igor Steinmacher

M

Marco Gerosa

A

Anita Sarma

Format Sitasi

Choudhuri, R., Liu, D., Steinmacher, I., Gerosa, M., Sarma, A. (2023). How Far Are We? The Triumphs and Trials of Generative AI in Learning Software Engineering. https://arxiv.org/abs/2312.11719

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2023
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓