Sentiment analysis using big data

The Web has become an excellent source for assembling consumer opinions. There are now several Web sites containing such opinions, e.g., customer reviews of products, forums, discussion groups, and blogs. This paper focuses on online customer reviews of products. It makes two contributions. First, it proposes a framework for analyzing and comparing consumer opinions of competing products in map and reduce environment for better analysis. Second, a new technique based on lexicon based technique is proposed to extract neutral reviews and restrict them from being categorized under positive or negative. Experimental results show that the technique is highly effective and smash existing methods significantly.