Otomatisasi Kerangka Kode dari Class Diagram: Pendekatan Generasi Berbasis Model

Alia Julyanti; Nadya Clarissa Az-zahra; Muhammad Ainul Yaqin

doi:10.55382/jurnalpustakadata.v6i4.2033

Penulis

Alia Julyanti Universitas Islam Negeri Maulana Malik Ibrahim Malang
Nadya Clarissa Az-zahra Universitas Islam Negeri Maulana Malik Ibrahim Malang
Muhammad Ainul Yaqin Universitas Islam Negeri Maulana Malik Ibrahim Malang

DOI:

https://doi.org/10.55382/jurnalpustakadata.v6i4.2033

Kata Kunci:

WMC, skeleton code, model-driven software engineering, class diagram, GPT-4

Abstrak

Hingga saat ini belum diketahui bagaimana kompleksitas class diagram memengaruhi kesesuaian struktural kode hasil luaran Large Language Model (LLM) secara kuantitatif. Penelitian ini mengevaluasi keandalan GPT-4 dalam mengotomatisasi generasi skeleton code Pascal menggunakan pendekatan Model-Driven Software Engineering (MDSE). Desain dari domain akademik, rumah sakit, dan e-commerce dievaluasi berdasarkan Weighted Methods per Class (WMC), jumlah kelas, dan kepadatan relasi menggunakan Jaccard Similarity. Hasil pengujian menunjukkan GPT-4 mencapai kesesuaian sempurna (1,00) pada kompleksitas rendah. Namun, akurasi menurun menjadi 0,935 (dokumen) dan 0,932 (gambar) pada skala menengah. Akurasi terendah terjadi pada skala tinggi (e-commerce), merosot hingga 0,845 (dokumen) dengan tingkat deviasi 15,5%, dan 0,910 (gambar) akibat halusinasi over-generation. Penelitian ini memberikan kontribusi berupa ambang batas empiris total WMC <= 15, di mana di atas nilai tersebut reliabilitas LLM turun di bawah 0,85 Jaccard similarity.

Unduhan

Data unduhan belum tersedia.

Referensi

I. A. Niaz, "Automatic Code Generation From UML Class and Statechart Diagrams," Ph.D. dissertation, Univ. of Tsukuba, Tsukuba, Japan, 2005.

M. Lauder, M. Schlereth, S. Rose, and A. Schürr, "Model-driven systems engineering: state-of-the-art and research challenges," Bulletin of the Polish Academy of Sciences: Technical Sciences, vol. 58, no. 3, pp. 389–405, 2010.

X. Hou et al., "Large Language Models for Software Engineering: A Systematic Literature Review," arXiv preprint arXiv:2308.10620, 2023.

H. Kanuka, G. Koreki, R. Soga, and K. Nishikawa, "Exploring the ChatGPT Approach for Bidirectional Traceability Problem between Design Models and Code," arXiv preprint arXiv:2309.14992, 2023.

S. R. Chidamber and C. F. Kemerer, "A metrics suite for object oriented design," IEEE Transactions on Software Engineering, vol. 20, no. 6, pp. 476–493, 1994.

T. Pradeep, A. K. Gonepally, A. K. Pusala, and C. T. Singarapu, "Anti-plagiarism tool helping developers to generate authentic code," International Journal of Science and Research Archive, vol. 14, no. 1, pp. 1208–1215, 2025.

T. Fouad and B. Mohamed, "Extracting UML Models and OCL Integrity Constraints From Object Relational Database," Journal of Theoretical and Applied Information Technology, vol. 96, no. 4, pp. 1138–1149, 2018.

C. Wang, B. Wang, P. Liang, and J. Liang, "Assessing UML Models by ChatGPT: Implications for Education," arXiv preprint arXiv:2412.17200, 2024.

H. M. Manoj and A. N. Nandakumar, "Constructing Relationship between Software Metrics and Code Reusability in Object Oriented Design," APTIKOM Journal on Computer Science and Information Technologies, vol. 1, no. 2, pp. 63–76, 2016.

Y. Song, C. Lothritz, D. Tang, T. F. Bissyandé, and J. Klein, "Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance," arXiv preprint, 2024.

F. Alomari and M. Harbi, "Scalable Source Code Similarity Detection in Large Code Repositories," EAI Endorsed Transactions on Scalable Information Systems, 2020.

C. N. Paradis, M. R. Yusuf, M. Farhanudin, and M. A. Yaqin, "Analisis dan Perancangan Software Pengukuran Metrik Skala dan Kompleksitas Diagram Class," JACIS: Journal Automation Computer Information System, vol. 2, no. 1, pp. 58–65, 2022.

I. Keivanloo, C. K. Roy, and J. Rilling, "Towards Source Code Clone Search via Information Retrieval," Univ. of Saskatchewan, Saskatchewan, Canada, Tech. Rep. #2014-02, 2014.

P. Kalyanasundaram and S. P. Ugale, "Model Transformation: Concept, Current Trends and Challenges," International Journal of Computer Applications, vol. 119, no. 14, pp. 33–37, 2015.

Z. Zheng et al., "Translating Regulatory Clauses into Executable Codes for Building Design Checking via Large Language Model Driven Function Matching and Composing," Preprints, 2025.

N. K. Maina, G. M. Muketha, and G. M. Wambugu, "A Literature Survey of Complexity Metrics for Object-Oriented Programs," International Journal of Science and Engineering Applications, vol. 11, no. 5, pp. 66–71, 2022.

M. Monteiro, B. C. Branco, S. Silvestre, G. Avelino, and M. T. Valente, "NoCodeGPT: A No-Code Interface for Building Web Apps with Language Models," arXiv preprint arXiv:2310.14843v2, 2024.

N. Nguyen and S. Nadi, "An Empirical Evaluation of GitHub Copilot's Code Generation Abilities," in Proceedings of the 19th International Conference on Mining Software Repositories, 2022.

C. Wu et al., "Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models," arXiv preprint arXiv:2303.04671, 2023.

M. Ozkaya, "Are the UML modelling tools powerful enough for practitioners? A literature review," IET Software, 2018.