Trust-based fusion of classifiers for static code analysis

摘要

Static code analysis tools automatically generate alerts for potential software faults that can lead to failures. However, developers are usually exposed to a large number of alerts. Moreover, some of these alerts are subject to false positives and there is a lack of resources to inspect all the alerts manually. To address this problem, numerous approaches have been proposed for automatically ranking or classifying the alerts based on their likelihood of reporting a critical fault. One of the promising approaches is the application of machine learning techniques to classify alerts based on a set of artifact characteristics. The effectiveness of many different classifiers and artifact characteristics have been evaluated for this application domain. However, the effectiveness of classifier fusion methods have not been investigated yet. In this work, we evaluate several existing classifier fusion approaches in the context of an industrial case study to classify the alerts generated for a digital TV software. In addition, we employ a trust-based classifier fusion method. We observed that our approach can increase the accuracy of classification by up to 4%.