Full Text PDF
Impact Factor (2025): 6.9
DOI Prefix: 10.47001/IRJIET
Impact Factor (2025): 6.9
DOI Prefix: 10.47001/IRJIET
Vol 10 No 5 (2026): Volume 10, Issue 5, May 2026 | Pages: 580-586
International Research Journal of Innovations in Engineering and Technology
OPEN ACCESS | Research Article | Published Date: 27-05-2026
Ensuring code correctness is essential in software development, but identifying and fixing syntax, logical, and runtime errors remains a major challenge for both beginners and experienced programmers. Traditional compilers and debugging tools provide limited feedback and often fail to suggest meaningful corrections or explain the root cause of errors, resulting in increased development time and reduced productivity. This paper presents an AI-powered code correction system capable of intelligently detecting and fixing programming errors across multiple languages, including Python, Java, C, and C++. The proposed system allows users to upload source code files, automatically analyzes the code using Abstract Syntax Tree (AST) parsing and dataset-driven learning techniques, and identifies syntax, logical, and runtime issues. By learning from a large collection of bug-fix pairs, the system predicts accurate corrections and generates improved code with contextual explanations for each fix. Additionally, the platform enables users to download the corrected source code file directly after processing, providing a complete and user-friendly debugging solution. Experimental results show that the system is lightweight, scalable, explainable, and effective in reducing debugging time while improving coding efficiency and learning support for programmers.
Abstract Syntax Tree (AST), Code Correction, File Upload System, Dataset-Driven Learning, Multi-Language Support, Syntax Error Detection, Logical Error Detection.
Kaveri Patil, Sakshi Gangurde, Neha Gavale, Prasad Shelar, Gaurav Patil, & A.B.Koli. (2026). AI-Powered Code Corrector Using Rule-Based Analysis. International Research Journal of Innovations in Engineering and Technology - IRJIET, 10(5), 580-586. Article DOI https://doi.org/10.47001/IRJIET/2026.105078
This work is licensed under Creative common Attribution Non Commercial 4.0 Internation Licence
R. Gupta, S. Pal, A. Kanade, and S. Shevade, “DeepFix: Fixing Common C Language Errors by Deep Learning,” in Proc. AAAI Conf. Artificial Intelligence, vol. 31, no. 1, 2017.
U. Ahmed et al., “Convolutional Neural Network Model for Syntax Error Detection in Programming,” Int. J. Artificial Intelligence & Applications, vol. 16, no. 2, 2025.
Z. Chen, S. Kommrusch, M. Tufano, and M. Monperrus, “SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair,” IEEE Trans. Software Engineering, vol. 47, no. 9, pp. 1943–1959, 2019.
E. A. Santos et al., “Syntax and Semantic Error Identification in English Writings using ML,” in IEEE Int. Conf. Software Maintenance and Evolution (ICSME), 2018.
M. Yasunaga and P. Liang, “DrRepair: Graph-based, Self-Supervised Program Repair from Diagnostic Feedback,” in Proc. ICML, 2020, pp. 10799–10808.
Y. Pu, K. Narasimhan, A. Solar-Lezama, and R. Barzilay, “skp: A Neural Program Corrector for Introductory Programming MOOCs,” in Proc. ACL, 2016.
W. Zhong et al., “Neural Program Repair: Systems, Challenges and Solutions,” Nature Computational Science, vol. 2, pp. 418–430, 2022.
H. Ye, M. Martinez, and M. Monperrus, “SelfAPR: Self- supervised Program Repair with Test Execution Diagnostics,” in Proc. ASE, 2022.
H. Ye, “Improving the Precision of Automatic Program Repair with Machine Learning,” Ph.D. dissertation, KTH Royal Institute of Technology, Stockholm, 2023.
Y. Li et al., “Automatic Program Repair via Learning Edits on Sequence Code Property Graph,” in Proc. ICSE, 2023.
F. Nyaga, “AI-Driven Software Engineering: A Systematic Review of Machine Learning’s Impact and Future Directions,” Preprints, 2025.
T. Lutellier et al., “CoCoNuT: Combining Context-Aware Neural Translation Models using Ensemble for Program Repair,” in Proc. ISSTA, 2020.
M. Allamanis, M. Brockschmidt, and M. Khademi, “Learning to Represent Programs with Graphs,” in Proc. ICLR, 2018.
M. Vasic, A. Kanade, and S. Petrovic, “Neural Program Repair by Jointly Learning to Localize and Repair,” in Proc. ICLR, 2019.
T. Crow et al., “Intelligent tutoring systems for programming education: a systematic review,” Computers & Education, vol. 122, pp. 128–140, 2018.
J. R. Anderson and B. J. Reiser, “The automated tutoring of introductory computer programming,” Communications of the ACM, vol. 29, no. 4, 1986.
S. S. Abu Naser, “Developing an Intelligent Tutoring Sys- tem For Students Learning C++,” Information Technology Journal, vol. 7, no. 7, 2008.
A.T. Corbett and J. R. Anderson, “Intelligent Tutoring Systems,” Handbook of Human-Computer Interaction, 1997.
W. L. Johnson, “Knowledge-based program understanding,” IEEE Trans. Software Engineering, 1985.
R. C. D. Reis et al., “AI-Powered Coding Tools: A Study of Advancements,” Journal of Systems and Software, vol. 185, 2025.
Z. Feng et al., “CodeBERT: A Pre-Trained Model for Programming and Natural Languages,” in Findings of ACL: EMNLP, 2020.
Y. Wang et al., “CodeT5: Identifier-aware Unified Pre- trained Encoder-Decoder Models,” in Proc. EMNLP, 2021.
M. Chen et al., “Evaluating Large Language Models Trained on Code (Codex),” arXiv:2107.03374, 2021.
Y. Wan et al., “Deep Learning for Code Intelligence: Survey, Benchmark and Toolkit,” ACM Computing Surveys, 2024.
J. Zhang et al., “A Survey on Deep Learning-Based Source Code Defect Analysis,” Journal of Systems and Software, 2020.
B. Roziere et al., “Code Llama: Open Foundation Models for Code,” arXiv:2308.12950, 2023.
IBM Research, “AI Code Review: Key components, tools, and benefits,” 2024.
P. Sestili et al., “A Review of Research on AI-Assisted Code Generation,” Artificial Intelligence Review, 2025.
CodeSubmit, “AI Code Tools: The Ultimate Guide in 2025,” Jan 2025. [Online]. Available: https://codesubmit.io/blog/ai- code-tools/
A.Mastropaolo et al., “On the Robustness of Code Generation Techniques: An Empirical Study on GitHub Copilot,” arXiv:2302.00438, 2023.
T. Szabo´, “Incrementalizing Production CodeQL Analyses,” in Proc. ESEC/FSE, 2023.