Classification of Authentic and Fake Online Reviews with Supervised Machine Learning Techniques

Online reviews are becoming more and more popular among consumers. Taking advantage of the Internet, consumers can read online reviews related to products or services, in order to make their purchase journey easier. In online review context, trust towards online reviews is an important determinant of customers' purchase intentions. The authenticity of online reviews can be a critical element in building trust toward reviews. However, based on prior experiences of consumers, online reviews may not always provide authentic information. Occasionally, fake reviews which do not reflect authentic product experiences, arrive on websites. In this regard, the detection, and thus prevention of fake reviews, gains great importance. The purpose of this study is to propose a new way to predict fake reviews by implementing supervised machine learning models. To achieve this, a dataset consisting of 1,600 reviews was used, and features were extracted from this dataset. A variety of supervised learning classifiers were trained by using features from the dataset, and then tested. The performance of each prediction model was compared using certain metrics, and the best result was acquired using the Random Forest (RF) Classifier.