Prediction of Opinion Behavior using Content based Sequential Opinion Influence Model

Abstract

Micro-blogging and social networking sites play a vital role in identifying and extracting distinct opinions and emotions from public. Social media has become a viral medium for public to express and exchange their opinions through the user-generated text. The aim of this paper is to classify the tweets using Content based algorithm and Support Vector Machine (SVM). The tweets are also analyzed and classified in terms of polarity: Positive, Negative and Neutral. To keep track of user opinion behaviors and infer user opinion influence from the historical exchanged textual information, we develop a contentbased sequential opinion influence framework with the help of two opinion sentiment prediction models with alternative prediction strategies are proposed.