An approach towards feature specific opinion mining and sentimental analysis across e-commerce websites

摘要

This research aims to automate the process of gathering online, end user reviews for any given product or service and analyzing those reviews in terms of the sentiments expressed about specific features. This involves the filtering of irrelevant and unhelpful reviews, quantification of the sentiments of thousands of (useful) reviews. And finally, providing the end user (business/manufacturer) summarized data about the expressed sentiments in way of intuitive and easy to understand graphs, charts and other visualization. This data can then be used to improve business outcomes and ensure a very high level of customer satisfaction.