소스코드 주제를 이용한 인공신경망 기반 경고 분류 방법 = Warning Classification Method Based On Artificial Neural Network Using Topics of Source Code

다국어 초록 (Multilingual Abstract)

Automatic Static Analysis Tools help developers to quickly find potential defects in source code with less effort. However, the tools reports a large number of false positive warnings which do not have to fix. In our study, we proposed an artificial neural network-based warning classification method using topic models of source code blocks. We collect revisions for fixing bugs from software change management (SCM) system and extract code blocks modified by developers. In deep learning stage, topic distribution values of the code blocks and the binary data that present the warning removal in the blocks are used as input and target data in an simple artificial neural network, respectively. In our experimental results, our warning classification model based on neural network shows very high performance to predict label of warnings such as true or false positive.

참고문헌 (Reference)

1 L. M. R. Velicheti, "Towards modeling the behavior of static code analysis tools" 17-20, 2014

2 Paul J. Werbos, "The Roots of Backpropagation: From Ordered Derivatives to Neural Networks and Political Forecasting" John Wiley & Sons 1994

3 N. Singh, "Short term electricity price forecast based on environmentally adapted generalized neuron" 125 : 127-139, 2017

4 J. Chang, "Reading tea leaves : How humans interpret topic models" 288-296, 2009

5 A. Yadav, "Ranking of software developers based on expertise score for bug triaging" 112 : 1-17, 2019

6 T. Hofmann, "Probabilistic latent semantic indexing" 50-57, 1999

7 K. Liu, "Mining fix patterns for findbugs violations" 2018

8 D. M. Blei, "Latent Dirichlet allocation" 3 : 993-1022, 2003

9 J. Wang, "Is there a golden feature set for static warning identification? : an experimental evaluation" 1-10, 2018

10 S. Deerwester, "Indexing by latent semantic analysis" 41 (41): 391-407, 1990

11 Z. P. Reynolds, "Identifying and documenting false positive patterns generated by static code analysis tools" 55-61, 2017

12 Q. Hanam, "Finding patterns in static analysis alerts : improving actionable alert ranking" ACM 152-161, 2014

13 S. Mani, "Deeptriage : Exploring the effectiveness of deep learning for bug triaging" 171-179, 2019

14 G. Ian, "Deep Learning" MIT Press 180-184, 2016

15 A. Goyal, "Cognitive Analytics: Concepts, Methodologies, Tools, and Applications" 1698-1725, 2020

16 U. Yüksel, "Automated classification of static code analysis alerts : A case study" 532-535, 2013

17 M. Beller, "Analyzing the state of static analysis : A large-scale evaluation in open source software" 470-481, 2016

18 S. Ruder, "An overview of gradient descent optimization algorithms"

19 S. Arai, "A gamified tool for motivating developers to remove warnings of bug pattern tools" 37-42, 2014