With the rapid development of mobile technologies, developing high-quality mobile apps becomes increasingly important. App reviews, which are collaboratively collected from various users, are viewed as important sources for enhancing or evolving mobile apps, wherein how to accurately extract feature requests becomes an important issue. However, the scale of app reviews is so large that it is intractable to manually identify feature requests from these reviews. In this paper, we propose a semi-automated approach to extract feature requests based on machine learning approaches. In our approach, we firstly identify reviews on feature requests by defining suitable classification features and selecting appropriate classification approaches. Afterwards, these identified reviews are clustered using topic models, and phrases are extracted as feature requests, which serve as the basis of feature modeling. Experiments conducted on a real world data set show that the proposed approach can contribute to extracting feature requests from app reviews.
CITATION STYLE
Peng, Z., Wang, J., He, K., & Tang, M. (2017). An approach of extracting feature requests from app reviews. In Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST (Vol. 201, pp. 312–323). Springer Verlag. https://doi.org/10.1007/978-3-319-59288-6_28
Mendeley helps you to discover research relevant for your work.