Social media platforms contain great wealth of information which provides usopportunities explore hidden patterns or unknown correlations, and understandpeople's satisfaction with what they are discussing. As one showcase, in thispaper, we summarize the data set of Twitter messages related to recentdemonetization of all Rs. 500 and Rs. 1000 notes in India and explore insightsfrom Twitter's data. Our proposed system automatically extracts the popularlatent topics in conversations regarding demonetization discussed in Twittervia the Latent Dirichlet Allocation (LDA) based topic model and also identifiesthe correlated topics across different categories. Additionally, it alsodiscovers people's opinions expressed through their tweets related to the eventunder consideration via the emotion analyzer. The system also employs anintuitive and informative visualization to show the uncovered insight.Furthermore, we use an evaluation measure, Normalized Mutual Information (NMI),to select the best LDA models. The obtained LDA results show that the tool canbe effectively used to extract discussion topics and summarize them for furthermanual analysis.
展开▼
