Deep learning or classical machine learning? An empirical study on line‐level software defect prediction

Author:

Zhou Yufei1,Liu Xutong2ORCID,Guo Zhaoqiang3ORCID,Zhou Yuming2ORCID,Zhang Corey4,Qian Junyan1ORCID

Affiliation:

1. Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education Guangxi Normal University Guilin Guangxi China

2. State Key Laboratory of Novel Software Technology Nanjing University Nanjing Jiangsu China

3. Huawei Technologies Co., Ltd Hangzhou Zhejiang China

4. Eastlake high school Washington USA

Abstract

AbstractBackgroundLine‐level software defect prediction (LL‐SDP) serves as a valuable tool for developers to detect defective lines with minimal human effort. Recently, GLANCE was proposed as a readily implementable baseline for assessing the efficacy of newly proposed LL‐SDP models.ProblemWhile DeepLineDP, a cutting‐edge LL‐SDP model rooted in deep learning, has demonstrated state‐of‐the‐art performance, it has not yet been compared against GLANCE.ObjectiveWe aim to empirically compare DeepLineDP with GLANCE to obtain a comprehensive understanding of how deep learning contributes to solving the LL‐SDP challenge.MethodWe compare GLANCE against DeepLineDP to assess the extent to which DeepLineDP surpasses GLANCE in predicting defective files and identifying problematic lines. In order to obtain a reliable conclusion, we use the same dataset and performance metrics utilized by DeepLineDP.ResultOur experimental findings indicate that DeepLineDP does not outperform GLANCE in LL‐SDP. This suggests that the application of deep learning, in this context, does not yield the anticipated significant improvements.ConclusionThis finding underscores the need for further research in deep learning‐based LL‐SDP to attain the state‐of‐the‐art performance that remains elusive for less advanced techniques.

Funder

National Natural Science Foundation of China

Natural Science Foundation of Guangxi Province

Publisher

Wiley

Reference63 articles.

1. DeepLineDP: Towards a Deep Learning Approach for Line-Level Defect Prediction

2. Code‐line‐level bugginess identification: how far have we come, and how far have we yet to go?;Guo Z;ACM Trans Softw Eng Methodol,2023

3. Predicting defective lines using a model‐agnostic technique;Wattanakriengkrai S;IEEE Trans Softw Eng,2022

4. On the “naturalness” of buggy code;Ray B;ICSE,2016

5. Bugram: bug detection with n‐gram language models;Wang S;ASE,2016

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3