Sentiment Analysis by Visual Inspection of User Data from Social Sites - A Review on Opinion Mining

Positive online reviews have a significant impact on customers decision-making process. On the other hand, online customer complaints, if not handled properly, could easily cause customers to lose loyalty for related products/services and create negative word-of-mouth. Thus, online customer feedback of products/service is useful for customer behavior analysis and is important for businesses. Customers can give their feedback in various websites and its difficult for product vendor/service provider or in case of our paper, hotel owner/manager to collect all reviews and analysis them. As a result, there is a growing need to extract and analyze customer opinions from large collections of online customer reviews. Recently, much effort has gone into automatic opinion mining, making it possible to obtain online customer opinions from various websites. However, visually examining and analyzing such mining results have not been well addressed in the past. Effective visual analysis of online customer opinions is needed, as it has a significant impact on building a successful business. In this paper, we present Opinion-Seer, an interactive visualization system that could visually analyze a large collection of online hotel customer reviews. The visual metaphor provides users with an integrated view of multiple correlations, allowing them to find useful opinion patterns quickly. Furthermore, it enables a fast side-by-side visual comparison of opinions of different customer groups, which is useful for finding out whether the opinions are influenced by a specific demographic factor