Review on Developing Corpora for Sentiment Analysis Using Plutchik’s Wheel of Emotions with Fuzzy Logic

Abstract

Internet is the global system which is increasing day by day with a faster rate. With the increasing internet, social networking increases and people started to share information through different kinds of social media. In recent years several efforts were devoted for mining opinions and sentiments automatically from natural language in social media messages, news and commercial product reviews. This task involves a deep understanding of the explicit and implicit information, conveyed by the language. Most of these approaches refer to annotated corpora. The use of Opinion mining is to identify and extract the information, which is in the subjective form from the internet. This can be done with the help of data, required for processing. The methods used are natural language processing, text analysis. Sentiments are also extracted from the feedbacks. Feedback is important for selling or purchasing any product. While shopping whenever someone wants to choose any product, the opinion of others will always help him/her to choose the best product. But it is very difficult for customer to read thousands of reviews at a time and it also creates confusion. So some data mining techniques must be applied to solve these problems. Sentiment analysis also helps in identifying the attitude of the person. In our work, we present a system which develops a corpus for opinion and sentiment analysis. We will take the product reviews and classify them as positive, negative and objective. The system will further classify the positive and negative sentiments into emotions using Plutchik’s wheel of emotions and makes a dictionary. It uses fuzzy logic approach for prediction and generates output.