Akihisa Yamada,Osamu Mizuno
Approaches to detect fault-prone modules have been studied for a long time. As one of these approaches, the authors proposed a technique using a text filtering technique. They assume that bugs relate to words and context that are contained in a software module. The technique treats a module as text information. Based on the dictionary which was learned by classifying modules which induce bugs, the bug inducing probability over a target module is calculated, and it judges whether the given module is a fault-prone module. The predictive granularity of this technique is a module. In this study, the authors aimed at prediction with the finer granularity of the portion that induces a bug. Specifically, they tried to predict bug-inducing changes by using source code differences of bug inducing changes and previous changes and a text filtering technique. Similarly, the authors tried to predict bug fixing by using source code differences of bug fixing changes and previous changes and a text filtering technique. To show the effectiveness of the approach, the authors conducted two experiments and compared their approach with fault-prone filtering by applying it to two open source projects, and obtained higher accuracy.
Akihisa Yamada,Osamu Mizuno
Akihisa Yamada,Osamu Mizuno
689
ACIS International Journal of Software Innovation
1
1
50-62
0
Classification of Bug Injected and Fixed Changes Using a Text Discriminator
DOI: 10.4018/ijsi.2015010104
3
2015
Osamu Mizuno,Hideaki Hata
Machine learning approaches have been widely used for fault-prone module detection. Introduction of machine learning approaches induces development of new software metrics for fault-prone module detection. We have proposed an approach to detect fault-prone modules using the spam- filtering technique. To use our approach in the conventional fault-prone module prediction approaches, we construct a metric from the output of spam-filtering based approach. Using our new metric, we conducted an experiment to show the effect of new metric. The result suggested that use of new metric as well as conventional metrics is effective for accuracy of fault-prone module prediction.
Osamu Mizuno,Hideaki Hata
Osamu Mizuno,Hideaki Hata
602
International Journal of Reliability and Safety
2
1
17-31
0
A Metric to Detect Fault-Prone Software Modules Using Text Classifier
7
2013
Hideaki Hata,Osamu Mizuno,Tohru Kikuno
This paper proposes an approach using large-scale text features for fault-prone module detection inspired by spam filtering. The number of every text feature in the source code of a module is counted and used as data for training detection models. In this paper, we prepared a naive Bayes classifier and a logistic regression model as detection models. To show the effectiveness of our approaches, we conducted experiments with five open source projects and compared them with a well-known metrics set, thereby achieving higher detection results. The results imply that large-scale text features are useful in constructing practical detection models, and measuring sophisticated metrics is not always necessary for detecting fault-prone modules.
DOI: 10.1007/s10664-009-9117-9
Hideaki Hata,Osamu Mizuno,Tohru Kikuno
Hideaki Hata,Osamu Mizuno,Tohru Kikuno
546
1.612 (2009)
Empirical Software Engineering
4
2
147-165
0
Fault-Prone Module Detection Using Large-Scale Text Features Based on Spam Filtering
http://www.springerlink.com/content/p7603rq2160756k4/
15
2010
Osamu Mizuno,Hideaki Hata
Machine-learning approaches have been widely used for fault-proneness detection. Introduction of machine learning approaches induces development of new software metrics for fault-prone module detection. We have proposed an approach to detect fault-prone modules using the spam-filtering technique. To treat our approach as the conventional fault-prone approaches, we summarize the output of spam-filtering based approach as a metric. In this paper, we show the effectiveness of our new metric comparing the conventional software metrics using two open source projects.
Osamu Mizuno,Hideaki Hata
Osamu Mizuno,Hideaki Hata
601
International Journal of Software Engineering and Its Application
1
1
43-52
0
Prediction of Fault-prone Modules Using A Text Filtering Based Metric
http://www.sersc.org/journals/IJSEIA/vol4_no1_2010.php
4
2010
Osamu Mizuno,Tohru Kikuno
This paper describes a novel approach for detecting fault-prone modules using a spam filtering
technique. Fault-prone module detection in source code is important for the assurance of software
quality. Most previous fault-prone detection approaches have been based on using software metrics.
Such approaches, however, have difficulties in collecting the metrics and constructing mathematical
models based on the metrics. Because of the increase in the need for spam e-mail detection, the
spam filtering technique has progressed as a convenient and effective technique for text mining. In
our approach, fault-prone modules are detected in such a way that the source code modules are
considered text files and are applied to the spam filter directly. To show the applicability of our
approach, we conducted experimental applications using source code repositories of Java based open
source developments. The result of experiments shows that our approach can correctly predict 78% of
actual fault-prone modules as fault-prone.
(C) 2008, IEICE.
Osamu Mizuno,Tohru Kikuno
Osamu Mizuno,Tohru Kikuno
524
0.369 (2008)
IEICE Trans. on Information and Systems
4
4
888-896
0
Prediction of Fault-Prone Software Modules Using a Generic Text Discriminator
http://www.ieice.org/jpn/trans_online/index.html
E91-D
2008
Tsuyoshi Fujiwara,Osamu Mizuno,Pattara Leelaprute
Researchers have studied approaches to detect fault-prone modules for a long time. As one of these approaches, we proposed an approach using a text filtering technique. In this approach, we assume that faults relate to words and contexts in a software module. Our technique accepts inputs as a text information. Based on a dictionary that was learned by classifying modules that induce faults, the fault inducing probability over a target module is calculated, and it judges whether the given module is a fault-prone module.
Although our approach targeted the source code of software, especially in embedded software, the analysis of byte-code is also required. The source code based fault detection suffered from noises such as the way of writing, the used name of identifiers, and so on. Eliminating such noises may improve the accuracy of prediction. In this study, we aimed at fault detection from the byte-code of Java. Specifically, we tried to detect faults from the disassembled intermediate code of Java class file. To show the effectiveness of our approach, we conducted an experiment and compared our approach with source code based approach.
10.1007/978-3-319-26844-630
Tsuyoshi Fujiwara,Osamu Mizuno,Pattara Leelaprute
Tsuyoshi Fujiwara,Osamu Mizuno,Pattara Leelaprute
Proc. of 16th International Conference on Product-Focused Software Process Improvement (PROFES2015), 1st International Workshop on Processes, Methods, and Tools for Engineering Embedded Systems
714
12
Bozen-Bolzano, Italy
9459
415-430
1
Fault-prone Byte-code Detection Using Text Classifier
LNCS
2015
Keita Mori,Osamu Mizuno
2015-07-01
Keita Mori,Osamu Mizuno
Keita Mori,Osamu Mizuno
Proc. of the 39th IEEE Computers, Software, and Applications Conference (COMPSAC 2015)
705
7
Taichung, Taiwan
609-612
1
IEEE CPS
An Implementation of Just-In-Time Fault-Prone Prediction Technique Using Text Classifier
2015
Akihisa Yamada,Osamu Mizuno
Approaches to detect fault-prone modules have been studied for a long time. As one of these approaches, we proposed a technique using a text filtering technique. We assume that bugs relate to words and context that are contained in a software module. Our technique treats a module as text information. Based on the dictionary which was learned by classifying modules which induce bugs, the bug inducing prob- ability over a target module is calculated, and it judges whether the given module is a fault-prone module. The predictive granularity of this technique is a module.
In this study, we aimed at prediction with the finer gran- ularity of the portion which induces a bug. Specifically, we tried to predict bug inducing changes by using source code differences of bug inducing changes and previous changes and a text filtering technique. Similarly, we tried to bug fixing predict by using source code differences of bug fixing changes and previous changes and a text filtering technique. To show the effectiveness of our approach, we conducted two experiments and compared our approach with fault-prone filtering by applying it to two open source projects, and obtained higher accuracy.
59%, 19/32
Akihisa Yamada,Osamu Mizuno
Akihisa Yamada,Osamu Mizuno
Proc. of 12th International Conference on Software Engineering Research, Management and Applications (SERA2014)
686
8
Kitakyushu, Japan
680-686
1
IEEE CPS
A Text Filtering Based Approach to Classify Bug Injected and Fixed Changes
DOI 10.1109/IIAI-AAI.2014.141
2014
Yukinao Hirata,Osamu Mizuno
In software development, defects affect quality and cost in an adverse way. Therefore, various studies have been conducted defect prediction. Among them, prediction using another project is important but it is one of the most difficult problem.
In this research, we conducted experiments that predict defects in Eclipse BIRT project using tokens from Eclipse and Netbeans projects as a training data by fault-prone filtering. Fault-prone filtering uses tokens in modules to classify the modules. Thus, investigating tokens are very important to improve prediction method. The result shows that fault-prone filtering can predict defects using another project tokens as a training data. In addition, we confirmed that the distribution of probability of faulty of tokens is significantly more important than the number of overlap between training tokens and test tokens.
Yukinao Hirata,Osamu Mizuno
Yukinao Hirata,Osamu Mizuno
Proc. of 22nd International Symposium on Software Reliability Engineering (ISSRE2011), Supplemental proceedings
649
11
Hiroshima, Japan
3-2
1
Investigating Effects of Tokens on Detecting Fault-prone Modules by Text Filtering
2011
Yukinao Hirata,Osamu Mizuno
Comment lines in the software source code include descriptions of
codes, usage of codes, copyrights, unused codes, comments, and so
on. It is required for comments to explain the content of written
code adequately, since the wrong description in the comment may
causes further bug and confusion in maintenance.
In this paper, we try to clarify a research question: ``In which
projects are comments described adequately?'' To answer this
question, we selected the group 1 of mining challenge and used data
obtained from Eclipse and Netbeans. Since it is difficult to answer
the above question directly, we define the distance between codes
and comments. By utilizing the fault-prone module prediction
technique, we can answer the alternative question from the data of
two projects. The result shows that Eclipse project has relatively
adequate comments.
Yukinao Hirata,Osamu Mizuno
Yukinao Hirata,Osamu Mizuno
Proc. of 8th Working Conference on Mining Software Repositories (MSR2011)
631
5
Honolulu, HI, USA
242-245
1
Do Comments Explain Codes Adequately? -- Investigation by Text Filtering --
2011
Osamu Mizuno,Hideaki Hata
In order to assure the quality of software product, early detection of fault-prone products is necessary. Fault-prone module detection is one of the major and traditional area of software engineering. However, comparative study using the fair environment rarely conducted so far because there is little data publicly available. This paper tries to conduct a comparative study of fault-prone module detection approaches.
Osamu Mizuno,Hideaki Hata
Osamu Mizuno,Hideaki Hata
Proc. of 34th Annual IEEE Computer Software and Applications Conference (COMPSAC2010)
615
7
Seoul, Korea
248-249
1
An Empirical Comparison of Fault-prone Module Detection Approaches: Complexity Metrics and Text Feature Metrics
2010
Osamu Mizuno,Hideaki Hata
Earlydetectionoffault-proneproductsisnecessarytoassurethequal- ity of software product. Therefore, fault-prone module detection is one of the major and traditional area of software engineering. Although there are many ap- proaches to detect fault-prone modules, they have their own pros and cons. Conse- quently, it is recommended to use appropriate approach on the various situations. This paper tries to show an integrated approach using two different fault-prone module detection approaches.
To do so, we prepare two approaches of fault-prone module detection: a text feature metrics based approach using naive Bayes classifier and a complexity metrics based approach using logistic regression. The former one is proposed by us and the latter one is widely used approach. For the data for application, we used data obtained from Eclipse, which is publicly available.
From the result of pre-experiment, we find that each approach has the pros and cons. That is, the text feature based approach has high recall, and complexity metrics based approach has high precision. In order to use their merits effectively, we proposed an integrated approach to apply these two approaches for fault-prone module detection. The result of experiment shows that the proposed approach shows better accuracy than each approach.
Osamu Mizuno,Hideaki Hata
Osamu Mizuno,Hideaki Hata
Proc. of 2010 International Conference on Advanced Science and Technology (AST2010)
610
6
Miyazaki, Japan
457-468
1
An Integrated Approach to Detect Fault-Prone Modules using Complexity and Text Feature Metrics
LNCS 6059
2010
開発の早期段階でソースコード中のfault-proneモジュールを特定することはプロダクトの品質向上につながる.これまでにもfault- proneモジュールを予測する多くの研究が行われてきたが,それらは全てメトリクスベースによるもので,ソフトウェアメトリクスの測定に余分な工数やコストがかかってしまう場合もある.そこで本研究では汎用のテキスト分類フィルタを利用したfault-proneモジュールの予測手法を提案する.具体的には,新たなモジュールを作成したときに,そのモジュールがfault-prone(FP)かnot-fault-prone(NFP)かをそのモジュールのソースコードをテキスト分類フィルタにかけることによって予測することを目指す.提案手法ではソースコードのみを用いて予測を行うので,何かある特定のソフトウェアメトリクスを測定するといった作業は必要としない.提案手法の有用性を示すために,ある開発言語がJavaのオープンソースソフトウェア開発プロジェクトのバージョン管理記録よりFPモジュールとNFPモジュールを抽出し,これらをテキスト分類フィルタにかけて実験を行った.そして実験の結果,70%近くのモジュールが正しく予測されたことを確認した.
井神 至朗,中市 秀哉,水野 修,菊野 亨
Shiro Ikami, Shuya Nakaichi, Osamu Mizuno, Tohru Kikuno
電子情報通信学会技術研究報告
499
2
愛知県立大学, 名古屋市
522, SS2006-75
25-30
3
汎用テキストフィルタを利用した不具合を含むソースコードの予測
Prediction of fault-prone source code modules using text classifier
106
2007
Keita Mori,Osamu Mizuno
Keita Mori,Osamu Mizuno
Keita Mori,Osamu Mizuno
COMPSAC 2015
707
0
8
Second Place COMPSAC 2015 Student Research Symposium (2015): An implementation of just-in-time fault-prone prediction technique using text classifier
2015