Can code metrics enhance documentation generation for computational notebooks?

Please enable javascript in your browser.

This page was sent successfuly

Bookmark

Mostafavi Ghahfarokhi, M ; Sharif University of Technology | 2024

99 Viewed

Type of Document: Article
DOI: 10.1145/3691620.3695334
Publisher: 2024
Abstract:
In software development, code documentation is crucial for collaboration and maintenance, especially as projects become more complex. However, it is often neglected due to the tedious effort it requires. This paper explores automating documentation generation for computational notebooks, focusing on the impact of code metrics such as lines of code, API popularity, and complexity on this task. Using a dataset of 22K code-documentation pairs, we compare deep learning models with and without code metric augmentation. The results show that incorporating these metrics significantly improves the accuracy of documentation generation, underscoring the connection between code metrics and quality documentation. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM
Keywords:
Computer software maintenance ; Deep learning ; System program documentation ; Code metrics ; Code quality ; Deep learning model ; Jupyter notebook ; Learning models ; Line of codes ; Software design
Source: Proceedings - 2024 39th ACM/IEEE International Conference on Automated Software Engineering, ASE 2024 ; 2024 , Pages 2472-2473 ; 979-840071248-7 (ISBN)
URL: https://dl.acm.org/doi/10.1145/3691620.3695334