Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 55260 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Heydarnoori, Abbas
- Abstract:
- Testing is one of the most important and time-consuming steps in the Software Development Life Cycle. Especially, in recent methodologies like agile in which change is an important feature and they take place in iterations with each iteration taking place in a limited time. Recent studies suggest approaches to automatically generate test cases for the applications. For GUI-based applications, test cases are composed of a chain of events that are activated by the user. For these applications, we can generate test cases by simulating the chain of events that get activated by the user. Semantic-based approaches use the semantic matching of the events and their related widgets, to generate test cases given the usage patterns of the applications or the test cases of similar applications. In this study, we intend to use domain-specific datasets to increase the semantic matching effectiveness in test reuse. Our domain-specific datasets are one composed of 900,805 application descriptions crawled from the Google Play Store, and the other, the same data set divided into 27 functionally similar applications. We then used these two datasets to train word embedding models, embedded those models in 48 different semantic matching configurations, and evaluated the final results given 337 unique queries extracted from previous similar studies. The calculated values of TOP1 and MRR metrics when using the general data set are respectively 0.5273 and 0.7101 on average. The calculated values for these metrics when using this data set after being divided into 27 domain-specific subsets are on average 0.5035 and 0.6907 respectively. Our results indicate that while the usage of domain-specific word embedding models improves semantic matching in the reuse of test cases of GUI applications, there is a turning point that specifies the ideal level of specialization.
- Keywords:
- Automated Test Data Generation ; Natural Language Processing ; Topic Modeling ; Word Embedding ; Semantic Matching ; Test Reuse
Digital Object List
محتواي کتاب
Bookmark