File(s) under permanent embargo
A system of systems service design for social media analytics
conference contribution
posted on 2023-05-23, 12:08 authored by Wong, RK, Chi, C, Yu, Z, Zhao, YMost social media analyses such as sentiment analysis for microblogs are often built as standalone, endpoint to endpoint applications. This makes the collaboration among distributed software and data service providers to create composite social analytic solutions difficult. This paper first proposes a system of systems service architecture (SoS-SA) design for social media analytics that support and facilitate efficient collaboration among distributed service providers. Then we propose a novel Twitters sentiment analysis service implemented on top of this design to illustrate its potentials. Current sentiment classification applications based on supervised learning methods relies too heavily on the chosen large training datasets, approaches using automatically generated training datasets also often result in the huge imbalance between the subjective classes and the objective classes in the sentiment of tweets, making it difficult to obtain good recall performance for the subjective ones. To address this issue, our proposed solution is based on a semi-supervised learning method for tweet sentiment classification. Experiments show that the performance of our method is better than those of the previous work.
History
Publication title
Proceedings of 2014 IEEE International Conference on Services ComputingEditors
E Ferrari, R Kaliappa, P HungPagination
789-796ISBN
978-1-4799-5066-9Department/School
School of Information and Communication TechnologyPublisher
IEEEPlace of publication
Piscataway, United StatesEvent title
2014 IEEE International Conference on Services ComputingEvent Venue
Anchorage, United StatesDate of Event (Start Date)
2014-06-27Date of Event (End Date)
2014-07-02Rights statement
Copyright 2014 IEEERepository Status
- Restricted