Sunman, NezihSoydan, YiğitSözer, Hasan2023-06-132023-06-132022-110164-1212http://hdl.handle.net/10679/8378https://doi.org/10.1016/j.jss.2022.111441There are fully automated approaches proposed for Web application testing. These approaches mainly rely on tools that explore an application by crawling it. The crawling process results in a state transition model, which is used for generating test cases. Although these approaches are fully automated, they consume too much time and they usually require manual configuration. This is due to the lack of insight and domain knowledge of crawling tools regarding the application under test. We propose a semi-automated approach instead. We introduce a tool that takes a set of recorded event sequences as input. These sequences can be captured during exploratory tests. They are replayed as pre-recorded test cases. They are also exploited for steering the crawling and test case generation process. We performed a case study with 5 Web applications. These applications were randomly tested with state-of-the-art tools. Our approach can reduce the crawling time by hours, while compromising the coverage achieved by 0.2% to 7.43%. In addition, our tool does not require manual configuration before crawling. The input for the tool was created within 15 min of exploratory testing..engrestrictedAccessarticle19300096798930000810.1016/j.jss.2022.111441Exploratory testingModel-based testingTest automationTest case generationWeb application testing2-s2.0-85134892412