Using Semi-Supervised Learning for Predicting Metamorphic Relations.

Software testing is difficult to automate, especially in programs which haveno oracle, or method of determining which output is correct. Metamorphictesting is a solution this problem. Metamorphic testing uses metamorphicrelations to define test cases and expected outputs. A large amount of time isneeded for a domain expert to determine which metamorphic relations can be usedto test a given program. Metamorphic relation prediction removes this need forsuch an expert. We propose a method using semi-supervised machine learning todetect which metamorphic relations are applicable to a given code base. Wecompare this semi-supervised model with a supervised model, and show that theaddition of unlabeled data improves the classification accuracy of the MRprediction model.