MINI PROJECT II
BASE PAPER :
Title: Using Artificial Intelligence to Convert Code to Another Programming
Language
Abstract:
This study presents a solution to the problem of automating the conversion of
program code between different programming languages using artificial
intelligence (AI) technologies This area is becoming increasingly relevant with
the development of multilingual projects and the need to integrate existing
solutions written in different programming languages. The difficulty of
translating code between programming languages lies not only in the syntactic
differences between languages, but also in preserving the semantics and logic of
the original code. Artificial intelligence can help to recognize patterns and
dependencies in the code, which will allow you to more effectively adapt the
code to the target language, taking into account its features. The use of machine
learning algorithms, in particular neural networks, allows you to develop
systems that can learn from code examples and independently improve their
conversion algorithms. Such systems analyze the abstract syntax tree (AST) of
the code, create intermediate representations, and generate the target code.
Various tools and platforms have been developed to simplify this process and
increase its accuracy. The process of code transformation with the help of AI is
used in many areas, including refactoring existing software, integrating systems
written in different languages, and in the educational process, where it can be
used to teach students the basics of different programming languages.
Citation:
Matsiievskyi, T. Honcharenko, O. Solovei, T. Liashchenko, I. Achkasov and V. Golenkov, "Using
Artificial Intelligence to Convert Code to Another Programming Language," 2024 IEEE 4th
International Conference on Smart Information Systems and Technologies (SIST), Astana, Kazakhstan,
2024, pp. 379-385, doi: 10.1109/SIST61555.2024.10629305.
keywords: {Training;Computer languages;Codes;Accuracy;Machine learning algorithms;Neural
networks;Training data;Artificial Intelligencet;AI;Neural Networks;abstract syntax tree;Programming
Language},
MINI PROJECT II
BASE PAPER 2:
TITLE: Analysis of ChatGPT-Generated Codes Across Multiple Programming
Languages.
Abstract:
Our research focuses on the intersection of artificial intelligence (AI) and
software development, particularly the role of AI models in automating code
generation. With advancements in large language models like ChatGPT,
developers can now generate code from natural language prompts, a task that
traditionally required significant manual input and expertise. AI-generated code
promises to boost productivity by enabling faster prototyping and automating
repetitive coding tasks. However, as these models are increasingly adopted in
real-world applications, questions surrounding their efficiency and code quality
become critical. This research investigates ChatGPT-4o, a state-of-the-art
language model, and its ability to generate functional, high-quality code in
different programming languages. By comparing performance between Python
and Java, the study seeks to shed light on AI’s capabilities and limitations in
code generation, addressing not only functional correctness but also broader
software engineering concerns such as memory usage, runtime efficiency, and
maintainability. The study addresses key questions related to the performance,
code quality, and error management of AI-generated code by analyzing
solutions for 300 data structure problems and 300 problems from the LeetCode
platform. The findings reveal notable performance differences between the two
languages: Java demonstrated superior runtime performance, particularly for
medium and hard problems, while Python exhibited better memory efficiency
across all complexity levels. The research also highlighted significant gaps in
code quality, with both languages showing deficiencies in documentation and
exception management. This study contributes to the literature by offering a
comprehensive cross-language analysis of ChatGPT-4o’s programming
capabilities, addressing a gap in the evaluation of AI-generated code
performance.
Citation :
S. Almanasra and K. Suwais, "Analysis of ChatGPT-Generated Codes Across
Multiple Programming Languages," in IEEE Access, vol. 13, pp. 23580-23596,
2025, doi: 10.1109/ACCESS.2025.3538050.
keywords: {Codes;Programming;Encoding;Chatbots;Runtime;Python;Software
development management;Java;Complexity theory;Standards;Artificial
MINI PROJECT II
intelligence;software development;ChatGPT;large language
model;programming},