Deep Learning Based Model for Fake Review Detection

In present time, peoples are more inclined towards the e-commerce for their purchases and their choices are much influenced by the reviews available over there as review plays an important role in making their decision. If the reviews are more positive the possibility to buy the product is comparatively high. Here, the necessity arrives to develop a sustainable approach for the detection of malicious reviews to save the customers from the fraud. There are many sites or agencies are available which are hired by the merchandise to generate the positive reviews for them to increase their sales or damage the competitor’s product sales. Deep learning methodologies for malicious review detection includes, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) are proposed in this paper. We have also compared the performance of these methods with state of arts techniques such as Naive Bayes (NB), K Nearest Neighbour (KNN) and Support Vector Machine (SVM) for the detection of fake reviews and ultimately, its efficiency is illustrated for both the traditional and the deep learning classifiers.