Software fault localization using feature selection

  • Authors:

  • Shounak Roychowdhury;Sarfraz Khurshid

  • Affiliations:

  • University of Texas at Austin, Austin, Texas;University of Texas at Austin, Austin, Texas

  • Venue:
  • Proceedings of the International Workshop on Machine Learning Technologies in Software Engineering
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

Manually locating and fixing faults can be tedious and hard. Recent years have seen much progress in automated techniques for fault localization. A particularly promising approach is to analyze passing and failing runs to compute how likely each statement is to be faulty. Techniques based on this approach have so far largely focused on either using statistical analysis or similarity based algorithms, which have a natural application in evaluating such runs. We present a novel approach to fault localization using feature selection techniques from machine learning. Our insight is that each additional failing or passing run can provide significantly diverse amount of information, which can help localize faults in code -- the statements with maximum feature diversity information can point to most suspicious lines of code. Experimental results show that our approach outperforms state-of-the-art approaches for localizing faults in most subject programs of the Siemens suite, which have previously been used to evaluate several fault localization techniques.