Exploring machine learning techniques for fault localization

Abstract

Debugging is the most important task related to the testing activity. It has the goal of locating and removing a fault after a failure occurred during test. However, it is not a trivial task and generally consumes effort and time. Debugging techniques generally use testing information but usually they are very specific for certain domains, languages and development paradigms. Because of this, a Neural Network (NN) approach has been investigated with this goal. It is independent of the context and presented promising results for procedural code. However it was not validated in the context of Object-Oriented (OO) applications. In addition to this, the use of other Machine Learning techniques is also interesting, because they can be more efficient. With this in mind, the present work adapts the NN approach to the OO context and also explores the use of Support Vector Machines (SVMs). Results from the use of both techniques are presented and analysed. They show that their use contributes for easing the fault localization task.