Text Mining Based Approach to Customer Sentiment Analysis Using Machine Learning | Original Article

ABSTRACT:

In the present competitive business scenario vast amount of consumer reviews are written on Web about any product or service whether available online or offline. Web stores a huge amount of customer reviews on any service or product popular amongst masses. The advent of social media and ecommerce has brought the era of a new age business and its customer base is growing exponentially every year. In today’s world, the online market is increasingly getting popular and it becomes more and more important to help the customer get the best product by all parameters. The quality of a product is best confirmed by taking the customer reviews from those who are already using that. All popular shopping websites like Amazon, flipkart, ebay etc allow customer reviews once the product has been purchased. These reviews are such huge in numbers on these websites that it is not possible for a customer to consider them all. The proposed work uses text mining techniques like Stanford parser, Sentiword Net and Wordnet 2.1 to parse and extract the sentiment from the reviews in the dataset. This research uses dataset from Amazon.com for musical instruments. The dataset is in JSON parser. The results received from the implementation of proposed technique ascertain the effectiveness of methodology. The computed results when compared to results obtained from Amazon using SVM and Naïve Bayes classifiers confirm that the proposed technique has better performance than the base research by Rushleen et al., who could best achieve 80 accuracy with the dataset adopted against 94.005 achieved by proposed technique. The results from Naive Bayes were found to be better and more explanatory for the inputted data.