Sentiment Analysis of Hotel Reviews

Abstract

Mining opinions and sentiments from natural language is challenging, because it requires a deep understanding of the explicit and implicit, regular and irregular, and syntactical and semantic language rules. Sentiment analysis actually focuses on polarity detection and emotion recognition, respectively. Sentiment keywords are best determined automatically which SentiWord Net for the most part does. SinceSentiWordNet outputs sentiment value, it is easy to classify the degree of sentiment. This paper proposes opinion mining applied on hotel reviews data using SentiWordNet. In this system, users can search the opinions for each hotel according to positive and negative senses with respect to Sentiment Analysis. Then, these analyzed results are summarized by using keywords.