Natural disaster topic extraction in Sina microblogging based on graph analysis

Abstract In this paper, we will propose a novel approach based on graph analysis which will use community structure detection algorithm to detect topics in the keywords graph of micro-blogging data. Furthermore, considering the specificity of the Sina microblogging, we propose novel keywords filtering model and graph generation algorithm to meet the dual requirements of topic detection and community detection. We validate our approach on a big natural disaster dataset from Sina micro-blog, in which about 10 3 micro-blogging posts with about 10 4 distinct feature tags. The experimental results definitely revealed the relationship between the keywords and the natural disaster topics. Our methodology is a scalable method which can adapt to the changes in the amount of data. Especially, we can get abundant information about natural disasters in the topic detection and help the government guide the rescue of disasters.