A Comprehensive Study of Sentimental Analysis Methods on Social Media Data | Original Article

ABSTRACT:

Sentiments and Opinions are only attributes to express views about attitude, emotions, and sentiments through various social networking sites like twitter, Facebook, Google+ but to categorize accurate positive and negative thoughts of peoples on social media data we have to use various sentimental analysis methods. In this research paper we discuss about various methods related to sentimental analysis and tabulate the accuracy of different techniques and comparing best methods to improve accuracy for social media data. In this research paper we compare various sentimental analysis methods related to classification techniques and create an analysis table for different supervised and unsupervised methods for different social media datasets and accuracy percentage for different techniques. In this research paper we compare various sentimental analysis methods related to classification techniques and create an analysis table for different supervised and unsupervised methods for different social media datasets and accuracy percentage for different techniques. Sentiment analysis relates to the problem of mining the sentiments from online available data and categorizing the opinion expressed by an author towards a particular entity into at most three preset categories: positive, negative and neutral. In this paper, firstly we present the sentiment analysis process to classify highly unstructured data on Twitter. Secondly, we discuss various techniques to carryout sentiment analysis on Twitter data in detail. Moreover, we present the parametric comparison of the discussed techniques based on our identified parameters.