Influence of Large Language Models on Programming Assignments – A user study

This study investigates the influence of chatbots based on general language models, such as ChatGPT, on the work of programmers. We developed a web application called ClueCodeChallenge that allows participants to solve JavaScript programming tasks and interact with a chatbot called ClueBot during the problem-solving process. A user study was conducted with 18 participants aged 19-28, where they completed two tasks, one of which had the option of using the chatbot. The results showed that participants took less time to solve tasks and made fewer errors when they could use the chatbot. The study also found that participants often preferred to ask the chatbot for the complete solution rather than using it as an aid to check their code or get clarification on the programming language. Our next steps are to expand the participant pool and explore the influence of different general language model chatbots on programming tasks across various programming languages.

Authors

Institutions

Publication Details

Published
2024-09-18
DOI
https://doi.org/10.1145/3702163.3702168
Citations
4
Primary Topic
Teaching and Learning Programming
Type
article
Field-Weighted Citation Impact
1.65
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Influence of Large Language Models on Programming Assignments – A user study

Alfonso Piscitelli, Gennaro Costagliola, Vittorio Fuccella, Mattia De Rosa
4 citations
Teaching and Learning Programming
1.65
article

Influence of Large Language Models on Programming Assignments – A user study

Alfonso Piscitelli, Gennaro Costagliola, Vittorio Fuccella, Mattia De Rosa
article en
4 citations

Abstract

This study investigates the influence of chatbots based on general language models, such as ChatGPT, on the work of programmers. We developed a web application called ClueCodeChallenge that allows participants to solve JavaScript programming tasks and interact with a chatbot called ClueBot during the problem-solving process. A user study was conducted with 18 participants aged 19-28, where they completed two tasks, one of which had the option of using the chatbot. The results showed that participants took less time to solve tasks and made fewer errors when they could use the chatbot. The study also found that participants often preferred to ask the chatbot for the complete solution rather than using it as an aid to check their code or get clarification on the programming language. Our next steps are to expand the participant pool and explore the influence of different general language model chatbots on programming tasks across various programming languages.

University of Salerno (IT)
Openalex Percentile: Top 11%
Teaching and Learning Programming
1.65
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Influence of Large Language Models on Programming Assignments – A user study — Alfonso Piscitelli, Gennaro Costagliola, et al. · (2024) | TGRS Research Map | TGRS