Social media has revolutionized the new-age customer's decision making through the myriads of sources available to them like online feedback or reviews, forum discussions, blogs and Twitter on the web. There is no need for them to depend on their peers any longer. When more convenient and efficient sources like user reviews are readily available to them over the internet. Vast and authentic information about all possible products ranges and services are at a click away. Even for commercial organization the task of gathering public opinion has been rendered tremendously easy, for the same reason that taking opinion polls and conducting surveys are now much simpler due to the abundance of information on the web. However, finding and monitoring opinion sites on the Web and filtering the information contained in them according to our need remains a difficult task because of the rapid increase in the number of distinct sites. Each site usually contains a huge volume of opinionated text which is difficult for any individual to go through. The average human reader will have difficulty identifying relevant sites and extracting and summarizing the opinions in them. Automated sentiment analysis systems are thus needed. This paper focuses on extracting the features from bank reviews taken from mouthshut. com and myBankTracker. com sites given by reviewers to state their opinions. This is done at aspect level of analysis using ontology. Then it determines whether they are positive or negative. Output of such analysis is then summarized.

Sentiment Analysis Opinion Mining Ontology Bank.