Using text clustering to predict defect resolution time: a conceptual replication and an evaluation of prediction accuracy

被引:13
作者
Assar, Said [1 ]
Borg, Markus [2 ]
Pfahl, Dietmar [3 ]
机构
[1] Inst Mines Telecom, Ecole Management, 9 Rue C Fourier, F-91011 Evry, France
[2] Lund Univ, Dept Comp Sci, Box 118, SE-22100 Lund, Sweden
[3] Univ Tartu, Inst Comp Sci, J Liivi 2, EE-50409 Tartu, Estonia
关键词
Defect resolution time; Prediction; Text mining; Data clustering; Independent replication; Simulation; BUG REPORTS; SOFTWARE;
D O I
10.1007/s10664-015-9391-7
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
Defect management is a central task in software maintenance. When a defect is reported, appropriate resources must be allocated to analyze and resolve the defect. An important issue in resource allocation is the estimation of Defect Resolution Time (DRT). Prior research has considered different approaches for DRT prediction exploiting information retrieval techniques and similarity in textual defect descriptions. In this article, we investigate the potential of text clustering for DRT prediction. We build on a study published by Raja (2013) which demonstrated that clusters of similar defect reports had statistically significant differences in DRT. Raja's study also suggested that this difference between clusters could be used for DRT prediction. Our aims are twofold: First, to conceptually replicate Raja's study and to assess the repeatability of its results in different settings; Second, to investigate the potential of textual clustering of issue reports for DRT prediction with focus on accuracy. Using different data sets and a different text mining tool and clustering technique, we first conduct an independent replication of the original study. Then we design a fully automated prediction method based on clustering with a simulated test scenario to check the accuracy of our method. The results of our independent replication are comparable to those of the original study and we confirm the initial findings regarding significant differences in DRT between clusters of defect reports. However, the simulated test scenario used to assess our prediction method yields poor results in terms of DRT prediction accuracy. Although our replication confirms the main finding from the original study, our attempt to use text clustering as the basis for DRT prediction did not achieve practically useful levels of accuracy.
引用
收藏
页码:1437 / 1475
页数:39
相关论文
共 67 条
[1]  
AbdelMoez W, 2013, 2013 INTERNATIONAL CONFERENCE ON TECHNOLOGICAL ADVANCES IN ELECTRICAL, ELECTRONICS AND COMPUTER ENGINEERING (TAEECE), P359
[2]   On Predicting the Time taken to Correct Bug Reports in Open Source Projects [J].
Anbalagan, Prasanth ;
Vouk, Mladen .
2009 IEEE INTERNATIONAL CONFERENCE ON SOFTWARE MAINTENANCE, CONFERENCE PROCEEDINGS, 2009, :523-526
[3]  
[Anonymous], 2002, RTI PROJECT
[4]  
[Anonymous], 2010, P 2010 ACM IEEE INT, DOI DOI 10.1145/1852786.1852814
[5]  
[Anonymous], DOCT S 29 IEEE ACM I
[6]  
[Anonymous], 2001, DATA ENG B, DOI 10.1.1.117.7676.
[7]  
[Anonymous], 1991, Replication Research in the Social Sciences
[8]  
[Anonymous], 2014, RECOMMENDATION SYSTE, DOI DOI 10.1007/978-3-642-45135-5_12
[9]  
[Anonymous], 2008, GUIDE ADV EMPIRICAL, DOI [10.1007/978-1-84800-044-5_14, DOI 10.1007/978-1-84800-044-5_14]
[10]  
[Anonymous], P 7 INT SOFTW METR S