Investigates the Impact of AI-generated Code Tools on Software Readability Code Quality Factor

Artificial Intelligence (AI) has made great strides in various industries, including software development, with tools such as ChatGPT changing the way code is written, maintained and developed. This study investigates the impact of AI-generated code on software quality, focusing on readability, code clarity, complexity, and documentation. Comparing AI-generated code with open-source code from GitHub for three tasks of varying difficulty (easy, medium, and hard), we evaluated key metrics such as cyclomatic complexity (CC), code lines, comment density, code-to-code ratio, and variable names. The results revealed that although both AI-generated and human-generated code can be concise and efficient, code generated by AI tools shows a greater focus on documentation more clearly. AI-generated code especially in complex tasks showed improved readability due to higher comment density and the use of clear variable names. These results show that AI tools such as ChatGPT can enhance code quality, especially in the software industry where readability and comprehensibility are critical.

Authors

Institutions

Publication Details

Published
2024-12-10
DOI
https://doi.org/10.1109/acit62805.2024.10876897
Citations
34
Primary Topic
Software Reliability and Analysis Research
Type
article
Field-Weighted Citation Impact
16.51
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Investigates the Impact of AI-generated Code Tools on Software Readability Code Quality Factor

Mohammed Khouj, Hamed Fawareh, Mohammed Al-Refai, Hazim M. Al-Shdaifat et al.
34 citations
Software Reliability and Analysis Research
16.51
article

Investigates the Impact of AI-generated Code Tools on Software Readability Code Quality Factor

Mohammed Khouj, Hamed Fawareh, Mohammed Al-Refai, Hazim M. Al-Shdaifat, Faid AlNoor Fawareh
article en
34 citations

Abstract

Artificial Intelligence (AI) has made great strides in various industries, including software development, with tools such as ChatGPT changing the way code is written, maintained and developed. This study investigates the impact of AI-generated code on software quality, focusing on readability, code clarity, complexity, and documentation. Comparing AI-generated code with open-source code from GitHub for three tasks of varying difficulty (easy, medium, and hard), we evaluated key metrics such as cyclomatic complexity (CC), code lines, comment density, code-to-code ratio, and variable names. The results revealed that although both AI-generated and human-generated code can be concise and efficient, code generated by AI tools shows a greater focus on documentation more clearly. AI-generated code especially in complex tasks showed improved readability due to higher comment density and the use of clear variable names. These results show that AI tools such as ChatGPT can enhance code quality, especially in the software industry where readability and comprehensibility are critical.

Zarqa University (JO), University of Business and Technology (SA)
Openalex Percentile: Top 1%
Software Reliability and Analysis Research
16.51
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.