Empirical Study And Analysis Of Software Bug Localization Approaches Using Deep Learning

Abstract

Bugs comes in high volume and documenting them properly in a specific format in the bug reports is difficult. Locating these bugs in correctly identified buggy files is a challenging task which needs to be automated. Numerous tools and techniques are proposed by researchers to support developers and testers to detect buggy files and automate the process of bug localization with greater accuracy. Recent research deal with the automation of Bug Localization process by using different techniques and tools. In this paper, we presented a comprehensive review of few papers in the domain of bug localization. This review helps us to know the benchmark datasets that are used in this process of bug localization, the major techniques that are worked upon, the findings and evaluation criteria and the architecture of various models and frameworks developed by researchers to automate the task of bug localization. This paper works on IR and DNN approaches and attempted to improve the previous results of DNNLOC successfully. The optimized version of the model improved the accuracy from 0.815 to 0.969 for enhanced rvsm and 0.83 to 0.971 for enhanced dnn. It is apparent that information retrieval approach and deep learning approach complement together in the domain of bug localization.