Key points are not available for this paper at this time.
Online reviews become a valuable source of information that indicates the overall opinion about products and services, which may affect decision-making processes such as purchase a product or service. Fake reviews are considered as spam reviews, which may have a great impact in the online marketplace behavior. Extracting useful features from review's text using Natural Language Processing (NLP) is not a straightforward step, in addition, it affects the overall performance and results. Many types of features could be used for conducting this task such as Bag-of-Words, linguistic features, words counts and n-gram feature. In this paper, we will investigate the effects of using two different feature selection methods on the spam reviews detection: Bag-of-Words and words counts. Different machine learning algorithms were applied such as Support Victor Machine, Decision Tree, Naïve Bayes and Random Forest. Experiments were conducted on a labeled balanced dataset of Hotels reviews. The efficiency will be evaluated according to many evaluation measures such as: precision, recall and accuracy.
Etaiwi et al. (Sun,) studied this question.