A Preliminary Study on Using Text- and Image-Based Machine Learning to Predict Software Maintainability

Markus Schnappinger, Simon Zachau, Arnaud Fietzke, Alexander Pretschner

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Machine learning has emerged as a useful tool to aid software quality control. It can support identifying problematic code snippets or predicting maintenance efforts. The majority of these frameworks rely on code metrics as input. However, evidence suggests great potential for text- and image-based approaches to predict code quality as well. Using a manually labeled dataset, this preliminary study examines the use of five text- and two image-based algorithms to predict the readability, understandability, and complexity of source code. While the overall performance can still be improved, we find Support Vector Machines (SVM) outperform sophisticated text transformer models and image-based neural networks. Furthermore, text-based SVMs tend to perform well on predicting readability and understandability of code, while image-based SVMs can predict code complexity more accurately. Our study both shows the potential of text- and image-based algorithms for software quality prediction and outlines their weaknesses as a starting point for further research.

Original languageEnglish
Title of host publicationSoftware Quality
Subtitle of host publicationThe Next Big Thing in Software Engineering and Quality - 14th International Conference on Software Quality, SWQD 2022, Proceedings
EditorsDaniel Mendez, Manuel Wimmer, Dietmar Winkler, Stefan Biffl, Johannes Bergsmann
PublisherSpringer Science and Business Media Deutschland GmbH
Pages41-60
Number of pages20
ISBN (Print)9783031041143
DOIs
StatePublished - 2022
Event14th International Conference on Software Quality, SWQD 2022 - Vienna, Austria
Duration: 17 May 202219 May 2022

Publication series

NameLecture Notes in Business Information Processing
Volume439 LNBIP
ISSN (Print)1865-1348
ISSN (Electronic)1865-1356

Conference

Conference14th International Conference on Software Quality, SWQD 2022
Country/TerritoryAustria
CityVienna
Period17/05/2219/05/22

Keywords

  • Expert judgment
  • Image classification
  • Machine learning
  • Maintainability prediction
  • Software maintainability
  • Text classification

Fingerprint

Dive into the research topics of 'A Preliminary Study on Using Text- and Image-Based Machine Learning to Predict Software Maintainability'. Together they form a unique fingerprint.

Cite this