Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{200948,
        author = {Mrs. S. Sharmila Bee and Elayaraja M and Ranjith Kumar K and Praisoodan R and Sathish E},
        title = {IntelliRefactor: An AI-Driven Semantic Code Improvement Framework},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {no},
        pages = {103-120},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=200948},
        abstract = {In modern software development environments, maintaining high-quality and well-structured source code is a major challenge due to the continuous evolution of software systems. As projects grow in size and complexity, source code often becomes difficult to understand, maintain, and modify. Code refactoring is a widely adopted software engineering practice that improves the internal structure of software without altering its external functionality. Refactoring helps developers reduce complexity, eliminate code smells, and improve maintainability. However, traditional refactoring techniques rely heavily on manual developer effort or rule-based static analysis tools that operate using predefined patterns and thresholds. These approaches are often limited in their ability to understand deeper semantic relationships within the code.
To address these limitations, this research proposes IntelliRefactor, an AI-driven semantic code improvement framework designed to automatically analyze Java source code and identify potential refactoring opportunities. The proposed system integrates static code analysis tools with machine learning techniques to improve the detection of code quality issues. JavaParser is used to parse Java source code and generate an Abstract Syntax Tree (AST) that represents the structural elements of the program. In addition, SonarQube is integrated to extract important code quality metrics such as cyclomatic complexity, maintainability index, and code smell indicators.
The extracted structural and quality features are processed using machine learning algorithms implemented through the Weka framework to identify patterns associated with poor code quality and maintainability issues. Based on this analysis, the system generates automated refactoring recommendations that assist developers in improving code readability and structure. The IntelliRefactor framework aims to reduce manual developer effort and improve software maintainability through intelligent code analysis and recommendation techniques.},
        keywords = {Sentiment Code Refactoring, Machine Learning, Static Code Analysis, Software Quality Metrics, Software Maintenance, JavaParser, SonarQube.},
        month = {May},
        }