Widget detection-based testing for industrial mobile games

• Main Authors: WU, Xiongfei, YE, Jiaming, CHEN, Ke, XIE, Xiaofei, HUANG, Ruochen, MA, Lei, ZHAO, Jianjun
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Game testing; Graphical user interface detection; Graphical user interface testing; Interface detection; Interface testing; Mobile game testing; Mobile games; Mobile gaming; Software quality assurance; Testing technique; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/8229; https://ink.library.smu.edu.sg/context/sis_research/article/9232/viewcontent/Widget_detection_based_testing_for_industrial_mobile_games.pdf
• Institution: Singapore Management University

The fast advances in mobile hardware and widespread smartphone usage have fueled the growth of global mobile gaming in the past decade. As a result, the need for quality assurance of mobile gaming has become increasingly pressing. While general-purpose testing methods have been developed for mobile applications, they become struggling when being applied to mobile games due to the unique characteristics of mobile games, such as dynamic loading and stunning visual effects. There comes a growing industrial demand for automated testing techniques with high compatibility (compatible with various resolutions, and platforms) and non-intrusive characteristics (without packaging external modules into the source code, e.g., POCO). To fulfill these demands, in this paper, we introduce our experience in adopting the widget detection-based testing technique WDTEST, for mobile games at NetEase Games. To this end, we have constructed by far the largest graphical user interface (GUI) dataset for mobile games and conducted comprehensive evaluations on the performance of state-of-the-art widget detection techniques in the context of mobile gaming.We leverage widget detection techniques to develop WDTEST, which performs automated testing using only screenshots as input. Our evaluation shows that WDTEST outperforms the widely used tool Monkey in achieving three times more coverage of unique UI in gaming scenarios. Our further experiments demonstrate that WDTEST can be applied to general mobile applications without additional fine-tuning. Furthermore, we conducted a thorough survey at NetEase Games to gain a comprehensive understanding of widget detection-based testing techniques and identify challenges in industrial mobile game testing. The results show that testers are overall satisfied with the compatibility testing aspect of widget detection-based testing, but not much with functionality testing. This survey also highlights several unique characteristics of mobile games, providing valuable insights for future research directions