TY - GEN
T1 - Emerging App Issue Identification from User Feedback
T2 - 41st IEEE/ACM International Conference on Software Engineering: Software Engineering in Practice, ICSE-SEIP 2019
AU - Gao, Cuiyun
AU - Zheng, Wujie
AU - Deng, Yuetang
AU - Lo, David
AU - Zeng, Jichuan
AU - Lyu, Michael R.
AU - King, Irwin
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/5
Y1 - 2019/5
N2 - It is vital for popular mobile apps with large numbers of users to release updates with rich features while keeping stable user experience. Timely and accurately locating emerging app issues can greatly help developers to maintain and update apps. User feedback (i.e., user reviews) is a crucial channel between app developers and users, delivering a stream of information about bugs and features that concern users. Methods to identify emerging issues based on user feedback have been proposed in the literature, however, their applicability in industry has not been explored. We apply the recent method IDEA to WeChat, a popular messenger app with over 1 billion monthly active users, and find that the emerging issues detected by IDEA are not stable (i.e., due to its inherent randomness, its results change when run multiple times even for the same inputs), and there are other problems such as long running time. To address these limitations, we design a novel tool, named DIVER. Different from IDEA, DIVER is more efficient (it can report real-Time alerts in seconds), generates reliable results, and most importantly, achieves higher accuracy in our practice. After its deployment on WeChat, DIVER successfully detected 18 emerging issues of WeChat's Android and iOS apps in one month. Additionally, DIVER significantly outperforms IDEA by 29.4% in precision and 32.5% in recall.
AB - It is vital for popular mobile apps with large numbers of users to release updates with rich features while keeping stable user experience. Timely and accurately locating emerging app issues can greatly help developers to maintain and update apps. User feedback (i.e., user reviews) is a crucial channel between app developers and users, delivering a stream of information about bugs and features that concern users. Methods to identify emerging issues based on user feedback have been proposed in the literature, however, their applicability in industry has not been explored. We apply the recent method IDEA to WeChat, a popular messenger app with over 1 billion monthly active users, and find that the emerging issues detected by IDEA are not stable (i.e., due to its inherent randomness, its results change when run multiple times even for the same inputs), and there are other problems such as long running time. To address these limitations, we design a novel tool, named DIVER. Different from IDEA, DIVER is more efficient (it can report real-Time alerts in seconds), generates reliable results, and most importantly, achieves higher accuracy in our practice. After its deployment on WeChat, DIVER successfully detected 18 emerging issues of WeChat's Android and iOS apps in one month. Additionally, DIVER significantly outperforms IDEA by 29.4% in precision and 32.5% in recall.
KW - Mobile apps
KW - anomaly
KW - app reviews
KW - emerging issue detection
UR - https://www.scopus.com/pages/publications/85072129753
U2 - 10.1109/ICSE-SEIP.2019.00040
DO - 10.1109/ICSE-SEIP.2019.00040
M3 - 会议稿件
AN - SCOPUS:85072129753
T3 - Proceedings - 2019 IEEE/ACM 41st International Conference on Software Engineering: Software Engineering in Practice, ICSE-SEIP 2019
SP - 279
EP - 288
BT - Proceedings - 2019 IEEE/ACM 41st International Conference on Software Engineering
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 25 May 2019 through 31 May 2019
ER -