Special Issue Article Open Access

Real Time Sentiment Classification Using Unsupervised Reviews

Abstract

Sentiment classification is an important task in everyday life. Users express their opinion about their product, movies and so on. All the web page contains reviews that are given by users expressing different polarity i.e. positive or negative. It is useful for both the producer and consumer to know what people think about the particular product or services based on their reviews. Automatic document classification is the task of classifying the reviews based on the sentiment expressed by the reviews. Sentiment is expressed differently in different domains. The data trained on one domain cannot be applied to the data trained on another domain. The cross domain sentiment classification overcomes these problems by creating thesaurus for labeled data on the target domain and unlabeled data from source and target domains. Sentiment sensitivity is achieved by creating thesaurus. The created thesaurus is used to expand the feature vector. Amazon reviews are taken from different products and the thesaurus is created for multiple domains which contain both positive and negative words. Thus the created sentiment sensitive thesaurus captures the words with similar sentiment. The proposed method the reviews are analyzed by unsupervised method and sentiment can be analyzed for each sentence.

E.Divya

To read the full article Download Full Article | Visit Full Article