Improve Classification of Commits Maintenance Activities with Quantitative Changes in Source Code

Richard Mariano, Geanderson Santos, Wladmir Brandão

Abstract

Software maintenance is an important stage of software development, contributing to the quality of the software. Previous studies have shown that maintenance activities spend more than 40% of the development effort, consuming most part of the software budget. Understanding how these activities are performed can support managers to previously plan and allocate resources. Despite previous studies, there is still a lack of accurate models to classify software commits into maintenance activities. In this work, we deepen our previous work, in which we proposed improvements in one of the state-of-art techniques to classify software commits. First, we include three additional features that concern the size of the commit, from the state-of-art technique. Second, we propose the use of the XGBoost, one of the most advanced implementations of boosting tree algorithms, and tends to outperform other machine learning models. Additionally, we present a deep analysis of our model to understand their decisions. Our findings show that our model outperforms the state-of-art technique achieving more than 77% of accuracy and more than 64% in the Kappa metric.

Download


Paper Citation


in Harvard Style

Mariano R., Santos G. and Brandão W. (2021). Improve Classification of Commits Maintenance Activities with Quantitative Changes in Source Code. In Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 2: ICEIS, ISBN 978-989-758-509-8, pages 19-29. DOI: 10.5220/0010401700190029


in Bibtex Style

@conference{iceis21,
author={Richard Mariano and Geanderson Santos and Wladmir Brandão},
title={Improve Classification of Commits Maintenance Activities with Quantitative Changes in Source Code},
booktitle={Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 2: ICEIS,},
year={2021},
pages={19-29},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010401700190029},
isbn={978-989-758-509-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 2: ICEIS,
TI - Improve Classification of Commits Maintenance Activities with Quantitative Changes in Source Code
SN - 978-989-758-509-8
AU - Mariano R.
AU - Santos G.
AU - Brandão W.
PY - 2021
SP - 19
EP - 29
DO - 10.5220/0010401700190029