This is a decommissioned version of ERA which is running to enable completion of migration processes. All new collections and items and all edits to existing items should go to our new ERA instance at https://ualberta.scholaris.ca - Please contact us at erahelp@ualberta.ca for assistance!
- 281 views
- 908 downloads
Machine learning driven software test case selection
-
- Author(s) / Creator(s)
-
After each software is developed, tests are carried out to identify defects that are subsequently deleted. But testing a non-trivial software completely is a really complex endeavor. Therefore, testing the software using critical test cases is important. Thus test case selection aims to minimize unnecessary test data, which is important for determining testing methods. In this study, we have created an approach for regression testing based on machine learning software tests. We initially clean the data and pre-process it in order to construct the approach. The category data is then converted to its numerical value. To generate a bag of characteristics for text features such as test case title, we apply natural language processing. For test cases selection we evaluate various machine learning models. The results of the experiments show that machine learning-based models can eliminate the need for domain experts to select test cases manually.
-
- Date created
- 2021-09-01
-
- Subjects / Keywords
-
- Type of Item
- Research Material