EFFICIENTLY ANALYZING AND DETECTING FAKE REVIEWS THROUGH OPINION MINING

Recently, Sentiment Analysis (SA) has become one of the most interesting topics in text analysis, due to its promising commercial benefits. One of the main issues facing SA is how to extract emotions inside the opinion, and how to detect fake positive reviews and fake negative reviews from opinion reviews. Moreover, the opinion reviews obtained from users can be classified into positive or negative reviews, which can be used by a consumer to select a product. The growth of e-commerce businesses has attracted many consumers, because they offer a range of products at competitive prices. One thing most purchaser rely on when they purchase online is for product reviews to conclude their decision. Many sellers use the decision to impact the review to hire the paid review authors. These paid review authors target the particular brand, store or product and write reviews to promote or demote them according to the requirements of their hired employees. This paper aims to classify Amazon product reviews into groups of positive or negative polarity by using machine learning algorithms. In this paper, we analyze online product reviews using SA methods in order to detect fake reviews. SA and text classification methods are applied to a dataset of product reviews. This paper focuses on detecting fake reviews from a set of product reviews by simulating fake reviews that incorporates various types of opinion spam review features and building a training set and then classifying it using Naïve Bayes classification and ensemble classification model like random forest to test the accuracy of the model.