期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2021
卷号：12
期号：11
DOI：10.14569/IJACSA.2021.0121137
语种：English
出版社：Science and Information Society (SAI)
摘要：User Experience (UX) provides insights into the users’ product perceptions while using or intending to use an application. Software products are known for complexity and changeability, starting from requirements engineering until the product operation. Users often evaluate software UX based on a prototype; however, UX is semantically embedded in the software requirements, a crucial indicator for project success. The problem of current UX evaluation methods is their dependence on the actual involvement of users or experts, a time-consuming process. First, this paper builds a benchmark dataset of UX based on textual software requirements crowdsourcing several UX experts. Second, the paper develops a machine learning model to measure UX based on the dataset. This research describes the dataset characteristics and reports its statistical internal consistency and reliability. Results indicate a high Cronbach Alpha and a low root mean square error of the dataset. We conclude that the new benchmark dataset could be used to estimate UX instantly without the need for subjective UX evaluation. The dataset will serve as a foundation of UX features for machine learning models.
