Date of Publication :17th August 2017

Abstract: Sentiment Analysis is an evolving field of research in text mining field. Nowadays, the opinions expressed through reviews are rising day by day on the web. It becomes practically unfeasible to analyze and extract opinions from such huge number of reviews manually. To overcome this problem an automated sentiment classification approach is needed. One aspect of study which is considered in this paper is to classify a given review tweet or paragraph whether it is of Positive[True-positive ,False-positive] or Negative[True-negative, False-negative] sentiment . In this paper a new approach is been proposed that uses lexicon database to assign each word in a text a value called score . The score is nothing but how a single word is affecting the whole sentence in which it is used. Every word in a sentence has its own strength and it tries to influence the overall semantic of the sentence. Higher the value of score of a word in the sentence, the more influential it is. The method proposed in this paper makes use of lexicon based approach as well as machine based learning. It uses AFINN lexicon database to assign score to words which is useful for sentiment classification and for testing and training the model the Support Vector Machine (SVM) and Naïve Bayes classifier (NB) machine learning algorithms are used

Reference :