A Big Data Parameter Estimation Approach to Develop Big Social Data Analytics Framework for Sentiment Analysis

Abstract

We are living in modern society, and mobile phones, tablets, laptops and personal computers have become part of our daily lives. These technologies are providing facility for social interaction and running all over the world through the expansion of Internet. The social media are producing huge amount of behavioral data through using different social media applications which such activities (likes, comments, share, etc.) have performed by users. This large volume of data can be generated in the form of structured, unstructured or semi-structured, and the 80 percent of social big data has been produced unstructured. By analyzing these data, we can predict people’s sentiments and opinions. This opinion we can use for business perspective such as ranking of any particular products, rating of online courses, rating of online shopping sites and human behavior of buying a car. In this paper, we have proposed a big social data analytics framework to analyze human behavior using sampling technique.