Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 53107 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Heydarnoori, Abbas
- Abstract:
- Mobile application marketplaces are not only a distribution platform but also a place for users to give feedback on their experience with application. User reviews contain useful information for software evolution tasks including bug reports, user experience, and feature requests. Considering the massive number of reviews that popular apps receive every day, manual inspection of reviews is not feasible in many cases. Researchers have developed automated tools to classify reviews into fixed and general-purpose categories related to software evolution in order to assist developers. Although this classification can reduce the time and effort for mobile developers, it does not consider the specific features and requirements of different app categories. In this research, we propose a semi-automatic approach to construct app-specific topic hierarchies for mobile apps and classify reviews accordingly. We use topic modeling to extract hidden topics related to software evolution from historical reviews, combined with expert knowledge of app developers to construct specific topic hierarchies for each app category. This topic hierarchy can later be used to classify new reviews by various degrees of granularity as they arrive, and help to extract detailed feedback for software evolution. Our evaluations on two case-studies show an overall of 85% accuracy in review classification, and practical usefulness of such approach in comparison to existing ones
- Keywords:
- Software Evaluation ; Classification ; User Reviews ; Topic Classification ; Mobile Application ; Topic Hierarchy
Digital Object List
-
محتواي کتاب
- view
Bookmark