Title
Missing standard features compared with similar apps? A feature recommendation method based on the knowledge from user interface
Abstract
To attract and retain users, deciding what features should be added in the next release of apps becomes very crucial. Different from traditional software, there are rich data resources in app markets to perform market-wide analysis. Considering that capturing key features that apps lack compared with its similar products and making up for them can be conducive to enhance the competitiveness, we propose a method to establish the feature relationships from the level of UI pages and recommend missing key features for the pages of apps based on these relationships. Firstly, we utilize the UI testing tool to collect UI pages for apps in the repository, and give the method to gain the feature information in them. Then, we identify the products similar to the analyzed app based on topic modeling technique. Finally, we establish the relationships between features by analyzing UI pages gained for the analyzed app as well as its similar products, and identify suitable features recommended to UI pages of the analyzed app based on these relationships. The experiment based on Google Play shows that our method can recommend features for apps from the level of UI pages effectively.
Year
DOI
Venue
2022
10.1016/j.jss.2022.111435
Journal of Systems and Software
Keywords
DocType
Volume
Android apps,Feature recommendation,User interface
Journal
193
ISSN
Citations 
PageRank 
0164-1212
0
0.34
References 
Authors
0
5
Name
Order
Citations
PageRank
Yihui Wang100.34
Shanquan Gao242.74
Xingtong Li300.34
Lei Liu455.46
Huaxiao Liu501.35