Spam Review Detection Using Deep Learning

Abstract

A robust and reliable system of detecting spam reviews is a crying need in today's world in order to purchase products without being cheated from online sites. In many online sites, there are options for posting reviews, and thus creating scopes for fake paid reviews or untruthful reviews. These concocted reviews can mislead the general public and put them in a perplexity whether to believe the review or not. Prominent machine learning techniques have been introduced to solve the problem of spam review detection. The majority of current research has concentrated on supervised learning methods, which require labeled data -an inadequacy when it comes to online review. Our focus in this article is to detect any deceptive text reviews. In order to achieve that we have worked with both labeled and unlabeled data and proposed deep learning methods for spam review detection which includes Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN) and a variant of Recurrent Neural Network (RNN) that is Long Short-Term Memory (LSTM). We have also applied some traditional machine learning classifiers such as Naïve Bayes (NB), K Nearest Neighbor (KNN) and Support Vector Machine (SVM) to detect spam reviews and finally, we have shown the performance comparison for both traditional and deep learning classifiers.

SeFACED: Semantic-Based Forensic Analysis and Classification of E-Mail Data Using Deep Learning

“…The LSTM has 3 gates to control the training process's information flow stated that LSTM is accurate. The yelp dataset is used to compare KNN, SVM, and NB algorithms with DL models [26].…”

A Method for Fast Selection of Machine-Learning Classifiers for Spam Filtering

“…The evaluation was performed on the e-mail spam dataset from UCI Machine-Learning Repository and Kaggle website. In [14], the problem of spam review detection is addressed. The authors proposed in their system deep-learning methods: Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), and a variant of Recurrent Neural Network (RNN) based on Long Short-Term Memory (LSTM) cells.…”

SAFER: Sentiment Analysis-Based FakE Review Detection in E-Commerce Using Deep Learning

“…Shahariar et al [15] proposed deep-learning models such as MLP, CNN, and LSTM for spam review detection. Apart from these three deep-learning models, traditional machine-learning models such as the NB, KNN, and SVM are also used, and later performance comparison was made with deep-learning models.…”

“…In the third category, although Yafeng et al [14] used CNN and RNN for fake review detection, the domain which has been considered are hotels, restaurants, and doctors and the maximum accuracy that they could achieve is 87.1%. Shahariar et al [15] in the same category applied deep-learning models but used a small dataset, which resulted in the overfitting problem. Rout et al [7] used a clustering approach k-NN for the unlabeled data and considered the electronics item reviews dataset to identify review spam.…”