Opinion Spam Detection based on Annotation Extension and Neural Networks

Abstract

Online reviews play an increasingly important role in the purchase decisions of potential customers. Incidentally, driven by the desire to gain profit or publicity, spammers may be hired to write fake reviews and promote or demote the reputation of products or services. Correspondingly, opinion spam detection has attracted attention from both business and research communities in recent years. However, unlike other tasks such as news classification or blog classification, the existing review spam datasets are typically limited due to the expensiveness of human annotation, which may further affect detection performance even if excellent classifiers have been developed. We propose a novel approach in this paper to boost opinion spam detection performance by fully utilizing the existing labelled small-size dataset. We first design an annotation extension scheme that uses extra tree classifiers to train multiple estimators and then iteratively generate reliable labelled samples from unlabeled ones. Subsequently, we examine neural network scenarios on a newly extended dataset to learn the distributed representation. Experimental results suggest that the proposed approach has better generalization capability and improved performance than state-ofthe-art methods.

Machine Learning-Based Opinion Spam Detection: A Systematic Literature Review

“…• The key challenges are a lack of proper deceptive review datasets and no access to spammers' identities the analysts. • The absence of fully labeled samples of truthful and fake reviews is considered one of the biggest challenges of online spam detection [30]. • Many studies on fake reviews crawl large samples of reviews and cluster them to find patterns and features that might reveal fakery [102].…”

“…There is very little spectrum for an SLR based on spam reviews. Although numerous studies attempted to construct different spam detector models [28][29][30], there is a lack of underlying research and technological solutions that assist in improving business performance. For example, deceptive review identification by a recurrent convolutional neural network (DRI-RCNN) was developed by Zhang, et al [31] using publicly available spam and deception datasets from TripAdvisor and Amazon Mechanical Turk.…”

A Review Structure Based Ensemble Model for Deceptive Review Spam

“…Feng et al [17] studied the distributions of rating scores and introduced strategies to create a dataset with pseudo-standard. Liu and Pang [18] trained multiple tree classifiers to generate labeled samples from unlabeled ones and train a neural network on the extended dataset.…”