DRI-RCNN: An approach to deceptive review identification using recurrent convolutional neural network

摘要

With the widespread of deceptive opinions in the Internet, how to identify online deceptive reviews automatically has become an attractive topic in research field. Traditional methods concentrate on extracting different features from online reviews and training machine learning classifiers to produce models to decide whether an incoming review is deceptive or not. This paper proposes an approach called DRI-RCNN (Deceptive Review Identification by Recurrent Convolutional Neural Network) to identify deceptive reviews by using word contexts and deep learning. The basic idea is that since deceptive reviews and truthful reviews are written by writers without and with real experience respectively, the writers of the reviews should have different contextual knowledge on their target objectives under description. In order to differentiate the deceptive and truthful contextual knowledge embodied in the online reviews, we represent each word in a review with six components as a recurrent convolutional vector. The first and second components are two numerical word vectors derived from training deceptive and truthful reviews, respectively. The third and fourth components are left neighboring deceptive and truthful context vectors derived by training a recurrent convolutional neural network on context vectors and word vectors of left words. The fifth and six components are right neighboring deceptive and truthful context vectors of right words. Further, we employ max-pooling and ReLU (Rectified Linear Unit) filter to transfer recurrent convolutional vectors of words in a review to a review vector by extracting positive maximum feature elements in recurrent convolutional vectors of words in the review. Experiment results on the spam dataset and the deception dataset demonstrate that the proposed DRI-RCNN approach outperforms the state-of-the-art techniques in deceptive review identification.