Title
Group Detection for Specific Topic on Micro-Blog
Abstract
In this paper, we focus on the problem of group detection on Sina micro-blog, the most popular micro-blogging system in China. Efficiency plays an extremely important role in data analysis. As a consequence, we propose a framework to quickly detect groups, in which we modify SimHash algorithm to calculate similarity of short text and improve TF-IDF algorithm to accurately calculate the weights. Basing on the framework, we analyze the characteristics of the sample groups and discover two new properties about groups. Besides, sentiment expressed in each group are studied and we find the consistency of attitude toward a specific topic within the same group. Extensive experiments on real-world social networks prove the high efficiency of the frame on group detection. Analysis of groups with this framework provide indispensable support for topic propagation.
Year
DOI
Venue
2016
10.1109/WISA.2016.36
2016 13th Web Information Systems and Applications Conference (WISA)
Keywords
DocType
ISBN
Group Detection,Big Data,SimHash,Topic,Sentiment Analysis
Conference
978-1-5090-5438-1
Citations 
PageRank 
References 
0
0.34
5
Authors
4
Name
Order
Citations
PageRank
Xiaolei Fu100.68
Ming Gao2244.78
Qiang Liu323.48
hongmei liu401.69