TY - GEN
T1 - A social sensing approach for quality changes of real-world services
AU - Shu, Qianqian
AU - Tu, Zhiying
AU - Xu, Xiaofei
AU - Wang, Zhongjie
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - In today's dynamic business environment, services keep changing and being updated to adapt to user demands evolution and technology trends continuously. Customers are eager for information about changes in the quality of services. So, they can make accurate decisions on service selection and get a better user experience. There are quite a lot of ways for service providers to actively promote their services, such as email notifications, mobile Apps notifications, real-world advertisements, etc. However, it is still difficult for customers to catch these changing information comprehensively and timely. Customers must have a quality changing sensing tool. Previous studies on quality sensing in services computing community are usually focused on simple web-based API services, and quality indicators to be sensed are usually technical-oriented. In this paper, we present a new approach for sensing service quality changes by social sensing. It makes use of publicly-disseminated news reports and user reviews on real-world services to identify what quality indicators are changing and which direction a change is towards (positive or negative). Deep learning is used for mining quality change information from a text corpus, and experiments conducted on real data of nursing home services show the effectiveness of the proposed method.
AB - In today's dynamic business environment, services keep changing and being updated to adapt to user demands evolution and technology trends continuously. Customers are eager for information about changes in the quality of services. So, they can make accurate decisions on service selection and get a better user experience. There are quite a lot of ways for service providers to actively promote their services, such as email notifications, mobile Apps notifications, real-world advertisements, etc. However, it is still difficult for customers to catch these changing information comprehensively and timely. Customers must have a quality changing sensing tool. Previous studies on quality sensing in services computing community are usually focused on simple web-based API services, and quality indicators to be sensed are usually technical-oriented. In this paper, we present a new approach for sensing service quality changes by social sensing. It makes use of publicly-disseminated news reports and user reviews on real-world services to identify what quality indicators are changing and which direction a change is towards (positive or negative). Deep learning is used for mining quality change information from a text corpus, and experiments conducted on real data of nursing home services show the effectiveness of the proposed method.
KW - Deep Learning
KW - Real-world Services
KW - Service Quality Changes
KW - Social Sensing
KW - Text Mining
UR - https://www.scopus.com/pages/publications/85092754921
U2 - 10.1109/SOSE49046.2020.00017
DO - 10.1109/SOSE49046.2020.00017
M3 - 会议稿件
AN - SCOPUS:85092754921
T3 - Proceedings - 14th IEEE International Conference on Service-Oriented System Engineering, SOSE 2020
SP - 82
EP - 91
BT - Proceedings - 14th IEEE International Conference on Service-Oriented System Engineering, SOSE 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 14th IEEE International Conference on Service-Oriented System Engineering, SOSE 2020
Y2 - 3 August 2020 through 6 August 2020
ER -