Automated evaluation of comments to aid software maintenance. Issue 7 (27th May 2022)

• Record Type: Journal Article
• Authors: Majumdar, Srijoni; Bansal, Ayush; Das, Partha Pratim; Clough, Paul D.; Datta, Kausik; Ghosh, Soumya Kanti
• Is Part Of: Journal of software. Volume 34:Issue 7(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-05-27
• Subjects: code comprehension -- comment quality -- knowledge graph -- machine learning -- ontology; Software engineering -- Periodicals; Computer software -- Development -- Periodicals; Software maintenance -- Periodicals; 005.1
• DOI: 10.1002/smr.2463
• Languages: English
• ISSNs: 2047-7473

Abstract

Abstract: Approaches to evaluate comments based on whether they increase code comprehensibility for software maintenance tasks are important, but largely missing. We propose Comment P r o b e for automated classification and quality evaluation of code comments of C codebases based on how they can help to understand existing code. We conduct surveys and document developers' perceptions on the type of comments that prove useful to maintaining software in the form of comment categories. A total of 20, 206 comments have been collected from open‐source Github projects and annotated with assistance from industry experts. We develop features to semantically analyze comments to locate concepts related to categories of usefulness. Additionally, features based on code and comment correlation are designed to infer whether the comment is also consistent and not superfluous. Using neural networks, comments are classified as useful, partially useful, and not useful with precision and recall scores of 86.27% and 86.42%, respectively. The proposed framework for comment quality evaluation incorporates industry practices and adds significant value to companies wanting to formulate better code commenting strategies. Furthermore, large codebases can be de‐cluttered by removing comments not helpful in maintaining code. Abstract : Analysis of developer's perception of comments that are relevant to comprehend code during software maintenance to formulate comment categories for C codebases. A semantic analysis framework for comments using textual and structural features based on comment categories and code–comment correlation. Automated quality analysis based on a machine learning approach.