Effectiveness of POS Tagging in Graph Based Sentiment Analysis Model

Abstract

In the recent times, deriving high quality information from the ever increasing amount of text data is highly desirable in many application domains. Analysis and summarization of review data is one such domain which demands an effective sentiment analysis technique. This paper proposes an efficient sentiment analysis model while establishing the importance of POS tagging in sentiment analysis. The model makes use of a graph based keyword extraction and domain specific polarity assignment technique. The proposed model outperforms few already established techniques for three review datasets.