AN APPLICATION FOR SENTIMENT ANALYSIS BASED ON EXPRESSIVE FEATURE IN THE SENTENCE

Our day-to-day life has always been influenced by what people think. Ideas and opinions of others have always affected our own opinions. As the Web plays an increasingly significant role in people's social lives, it contains more and more information concerning their opinions and sentiments. The distillation of knowledge from this huge amount of unstructured information, also known as opinion mining and sentiment analysis. Nowadays, with the rapid evolution of smart phones, mobile applications (Mobile Apps) have become essential parts of our lives. However, it is difficult for consumers to keep track and understand the app sphere because new apps are entering market every day. Such a large amount of apps seems to be a great opportunity for customers to buy from a wide selection range. But, first they have to understand what the apps do, how are they viewed by other consumers and then they have to purchase the apps to use on their smart phones. Typically, online customer reviews contain two parts, ratings and textual comments. Rating indicates the overall evaluation of customer experiences using a numeric scale, but textual comments are capable of telling more insightful stories that the overall ratings cannot. It is very challenging for a potential user to read all of them to make a decision. Also, app developers have difficulties in finding out how to improve the app performance based on overall ratings alone and would benefit by understanding the thousands of textual comments. In proposed approach, user reviews are summarized and features are extracted from the apps mentioned in the reviews. Then, NLP approach is used for writing rules and then sentiment analyzer is used for the analysis of sentiments that are arising through the textual comments of users.