Towards Automatically Generating Release Notes using Extractive Summarization Technique
Related items loading ...
Section 1: Publication
Publication Type
Journal Article
Authorship
Sumana SN and Roy B
Title
Towards Automatically Generating Release Notes using Extractive Summarization Technique
Year
2021
Publication Outlet
The 33rd International Conference on Software Engineering & Knowledge Engineering (SEKE), KSIR Virtual Conference Center, Pittsburgh, USA
DOI
ISBN
ISSN
Citation
Sumana SN and Roy B, Towards Automatically Generating Release Notes using Extractive Summarization Technique, The 33rd International Conference on Software Engineering & Knowledge Engineering (SEKE), KSIR Virtual Conference Center, Pittsburgh, USA, 2021, pp. 241-248.
Abstract
Release notes are admitted as an essential document by practitioners. They contain the summary of the source code changes for the software releases, such as issue fixes, added new features, and performance improvements. Manually producing release notes is a time-consuming and challenging task. For that reason, sometimes developers neglect to write release notes. For example, we collect data from GitHub with over 1,900 releases, among them 37% of the release notes are empty. We propose an automatic generate release notes approach based on the commit messages and merge pull-request (PR) titles to mitigate this problem. We implement one of the popular extractive text summarization techniques, i.e., the TextRank algorithm. However, accurate keyword extraction is a vital issue in text processing. The keyword matching and topic extraction process of the TextRank algorithm ignores the semantic similarity among texts. To improve the keyword extraction method, we integrate the GloVe word embedding technique with TextRank. We develop a dataset with 1,213 release notes (after null filtering) and evaluate the generated release notes through the ROUGE metric and human evaluation. We also compare the performance of our technique with another popular extractive algorithm, latent semantic analysis (LSA). Our evaluation results show that the improved TextRank method outperforms LSA.
Plain Language Summary
Section 2: Additional Information
Program Affiliations
Project Affiliations
Submitters
Publication Stage
Published
Theme
Presentation Format
Additional Information
Computer Science Core Team, Refereed Publications