Lexicon based Acronyms and Emoticons Classification of Sentiment Analysis (SA) on Big Data

Abstract

Sentiment Analysis plays a vital role in the domain of Big Data. Especially, Sentiment Analysis is the process to determine the text based analysis. Particularly, Twitter social media network allows 140 characters for text limitation. So people can convey their emotions by using emoticons, proper and improper text. Improper text is named as acronyms, the acronyms and emoticons are the greatest challenging issues for classifying and evaluating the opinions. The issues like sentiments, acronyms and emoticons have distinct meaning. So they are isolated. Then the classified emotions could be formulated in different classes like positive, negative and neutral emotions. In this paper, a new algorithm named Senti_Acron which has been proposed to detect the polarity and classify the different classes. The acronyms and emoticons have matched with Synset and SemEval dictionary words and extract the semantic words from the data set. Whereas, the features are selected with a help of equations to measure the frequent occurrences of a sentiment and assigned ranking for the sentiment based on the occurrences. The result of the proposed work Senti_Acron is 0.6875, in percentage 68.75% which provides enhanced accuracy.