Opinion Mining Framework For News Reviews To Build Good Customer Loyalty

摘要

In the era of third generation platform, users share information and news using social media (wikis, blogs, forums and social networks) through all digital communication devices. The social media contents include important, honest news, and other is malicious, one of the third generation platform challenges is the news credibility judgment, and avoiding the problems of the false information. Opinion mining is also called sentiment analysis, it is the process of understanding the attitudes from text patterns, and analyzing it to extract valuable information from large amount of data. As the online news researcher can't determine whether the news was believable or not so the opinion mining can determine the credibility of the news from which the reader can get his/ her information. In this paper we proposed a new opinion mining framework for selecting the higher accuracy classifier, which takes the lowest required time to build the model for movie news reviews sentiment analysis. The experiments showed that Support Vector Machine and Naïve Bayes Multinomial produced the highest accuracy, but the second reduced the time required to build the model much more than the first.