Survey on Dual Sentiment Analysis

Abstract: Mining opinion targets and opinion words from online reviews of products (Custom portal) are important tasks for fine-grained opinion mining, the key component of which involves detecting opinion relations among words (target words). In this system user can add their reviews about the product and the system can extract the target words and opinion relation. By using the opinion and targets to find out the sentiment analysis about the reviews. Reviews contains the compound sentence then it will split it into the separate sentence and find the targets and opinion and also sentiment from reviews. The system is then reversing the Negative opinion sentences into Positive. The sentiment can be negative, positive, neutral, vary negative and very positive. Then all the sentiments, targets and the opinion about the product are represented using the graphical format. All comments will be stored in Hadoop and Analysis will be done on comments using Hadoop.

Keywords: Hadoop, Data Mining, Sentiment Analysis.