Coronavirus pandemic analysis through tripartite graph clustering in online social networks

The COVID-19 pandemic has hit the world hard. reaction to related issues been pouring into social platforms, such as Twitter. Many public officials and governments use Twitter make policy announcements. People keep close track of information express their concerns about policies on It is beneficial yet challenging derive important or knowledge out data. In this paper, we propose a Tripartite Graph Clustering for Pandemic Data Analysis (TGC-PDA) framework that builds proposed models analysis: (1) tripartite graph representation, (2) non-negative matrix factorization with regularization, (3) sentiment analysis. We collect tweets containing set keywords coronavirus ground truth Our can detect communities users analyze topics are discussed in communities. extensive experiments show our TGC-PDA effectively efficiently identify correlations within data monitoring understanding opinions, which would provide makers useful statistics decision making.