Analysing the Social Data Opinion through Public User Raw Information

Abstract

The social network perspective provides a set of methods for revealing the structure of social networks as well as a variety of hypothesis explaining the patterns discovered in these structures. The study of these structures uses social network discovering to recognizing local and global patterns; locate influential entities, and proficiency network dynamics. Millions of users share their opinions on Social Networks, making it a valuable platform for tracing and analyzing public sentiment. Such tracking and analysis can provide critical information for decision making in various domains. Therefore it has captivated attention in both academia and industry. This approach needs Sentimental data analysis model using Neural Networks. Both positive and negative also comments will be calculated here. To further enhance the readability of the mined reasons, we select the most representative tweets for foreground topics and develop another generative model called Reason Candidate and Background LDA (RCB-LDA) to rank them with respect to their popularity within the variation period. Experimental results show that our methods can effectively find foreground topics and rank reason candidates.