Fake Review Detection Research Articles

Mining behavioural and sentiment-dependent linguistic patterns from restaurant reviews for fake review detection

Online reviews are increasingly recognized as a key source of information influencing consumer behavior. This in turn implies that competitive advantage can be achieved by manipulating users’ perceptions about restaurants. The hospitality industry is particularly susceptible to this issue because products and services in this industry can only be rated upon consumption. Therefore, many efforts have recently been dedicated to developing automatic methods for detecting fake reviews based on data intelligence in this sector. Recent studies suggest that both the semantic meaning of consumer reviews and the sentiment conveyed may be useful indicators of fake reviews. However, the semantic meaning may be context-sensitive and may also disregard sentiment information. Moreover, the content analysis approach should be integrated with the reviewer's behavior to reveal their true intentions. To address these problems, we propose a review representation model based on behavioural and sentiment-dependent linguistic features that effectively exploit the domain context. Using a large dataset of Yelp restaurant reviews, we demonstrate that the proposed review representation model is more effective than existing approaches in terms of detection accuracy. It furthermore accurately estimates the average rating assigned by legitimate reviewers, which has significant managerial implications for the hospitality industry.

The Effect of Fake Reviews on e-Commerce During and After Covid-19 Pandemic: SKL-Based Fake Reviews Detection

The outbreak of Covid-19 and the enforcement of lockdown, social distancing, and other precautionary measures lead to a global increase in online shopping. The increasing significance of online shopping and extensive use of e-commerce has increased competition between companies for online selling. Highlights that online reviews play a significant role in boosting a business or slandering it. Product review is an essential factor in customers’ decision-making, leading to an intense topic known as fraudulent or fake reviews detection. Given these reviews’ power over a business, the treacherous acts of giving false reviews for personal gains have increased with time. In our research, we proposed a fake review detection model by using Text Classification and techniques related to Machine Learning. We used classifiers such as Support Vector Machine, K-Nearest Neighbor, and logistic regression (SKL), using a bigram model that detects fraudulent reviews based on the number of pronouns, verbs, and sentiments. Our proposed methodology for detecting fake online reviews outperforms on the yelp dataset and the TripAdvisor dataset compared to other state-of-the-art techniques with 95% and 89.03% accuracy.

Fake Online Reviews: A Unified Detection Model Using Deception Theories

Online reviews influence consumers’ purchasing decisions. However, identifying fake reviews online automatically remains a complex problem, and current detection approaches are inefficient in preventing the spread of fake reviews. The literature on fake reviews detection lacks a comprehensive and interpretable theory-based model with high performance, which enables us to understand the phenomenon from a psychological perspective and analyze reviews based on user-generated content as well as consumer behavior. In this research, we synthesized ten well-founded deception theories from psychology, namely leakage theory, four-factor theory, interpersonal deception theory, self-presentational theory, reality monitoring theory, criteria-based content analysis, scientific content analysis, verifiability approach, truth-default theory, and information manipulation theory, and selected nine relevant constructs to develop a unified model for detecting fake online reviews. These constructs include specificity, quantity, non-immediacy, affect, uncertainty, informality, consistency, source credibility, and deviation in behavior. We characterized the selected constructs using verbal and non-verbal features to validate the proposed model empirically. Subsequently, we extracted features from the Yelp datasets and used them to train four machine learning algorithms, specifically Logistic Regression, Naïve Bayes, Decision Tree, and Random Forest. We demonstrated that quantity, non-immediacy, affect, informality, consistency, source credibility, and deviation in behavior are essential constructs for detecting fake reviews. To our surprise, we discovered that non-verbal features are more important than verbal features and that combining features from both types improves the prediction performance. Our theory-based model outperformed most of the state-of-the-art fake review detection models and yielded high interpretability and low complexity.

Comparative Analysis of Fake Review Monitoring and Detection using Logistic Regression, Decision Tree, Support Vector Machine

Comparative Analysis of Fake Review Monitoring and Detection using Logistic Regression, Decision Tree, Support Vector Machine

Do Reviewers’ Words and Behaviors Help Detect Fake Online Reviews and Spammers? Evidence From a Hierarchical Model

Although numerous studies have investigated spam detection and spammer detection on online platforms, they have ignored the fact that reviews written by the same reviewer may be correlated because each reviewer has their own distinct style. The traditional logistic regression model cannot handle this type of data because they violate the independence of residuals assumption. Furthermore, relatively few studies related to fake review detection have considered linguistic and behavioral aspects simultaneously. Thus, we propose a hierarchical logistic regression (HLR)-based model for detecting fake reviews that considers both linguistic and behavioral characteristics. With this outcome, our kernel also has multiple applications, including the detection of review spammers as a pre-module of quality in machine learning. The experimental results demonstrate that HLR can classify fake reviews and review spammers more accurately than the standard machine-learning algorithms.

Joint Sentiment Topic Model with Word Embeddings for Fake Review Detection

Joint Sentiment Topic Model with Word Embeddings for Fake Review Detection

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

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

The Detection of Fake Reviews in Bestselling Books

This study detected the possible manipulation of reviews for bestseller books. The authors first used clustering analysis to identify the cluster of bestselling books and patterns of manipulated reviews and ratings. They then used an artificial neural network to predict the possibility of review manipulation in bestselling books based on the patterns identified. The prediction outcome has an accuracy rate of 89%. They found that fake or manipulated reviews for bestselling books could be identified by analyzing abnormal rating fluctuations. The findings could help e-commerce platforms identify review manipulations and thereby help customers make prudent purchase decisions.

Fuzzy artificial bee colony‐based CNN‐LSTM and semantic feature for fake product review classification

SummaryIn recent years, online reviews are considered as the most significant resource for consumers to make a decision regarding the purchase of a particular product. The reviews can either encourage or relegate a product; therefore posting fake reviews has turned into a money‐spinning business in the modern period. The detection of fake reviews has become a center of attraction for various business people. This research study aims in detecting fake product reviews using four significant phases namely the data pre‐processing, feature extraction, feature selection, and classification. The features obtained in the pre‐processing phase are extracted and selected using chi‐squared technique to obtain a delegate subset among all data and to reduce the complication issues. Then a CNNLSTM‐FABC approach classifies and detects the review as fake or real. Finally, the performance evaluation and the comparative analysis are carried out to determine the effectiveness of the proposed approach. The results reveal that the proposed approach performs well irrespective of the product type and sentiment polarity.

What Yelp Fake Review Filter Might Be Doing?

Online reviews have become a valuable resource for decision making. However, its usefulness brings forth a curse ‒ deceptive opinion spam. In recent years, fake review detection has attracted significant attention. However, most review sites still do not publicly filter fake reviews. Yelp is an exception which has been filtering reviews over the past few years. However, Yelp’s algorithm is trade secret. In this work, we attempt to find out what Yelp might be doing by analyzing its filtered reviews. The results will be useful to other review hosting sites in their filtering effort. There are two main approaches to filtering: supervised and unsupervised learning. In terms of features used, there are also roughly two types: linguistic features and behavioral features. In this work, we will take a supervised approach as we can make use of Yelp’s filtered reviews for training. Existing approaches based on supervised learning are all based on pseudo fake reviews rather than fake reviews filtered by a commercial Web site. Recently, supervised learning using linguistic n-gram features has been shown to perform extremely well (attaining around 90% accuracy) in detecting crowdsourced fake reviews generated using Amazon Mechanical Turk (AMT). We put these existing research methods to the test and evaluate performance on the real-life Yelp data. To our surprise, the behavioral features perform very well, but the linguistic features are not as effective. To investigate, a novel information theoretic analysis is proposed to uncover the precise psycholinguistic difference between AMT reviews and Yelp reviews (crowdsourced vs. commercial fake reviews). We find something quite interesting. This analysis and experimental results allow us to postulate that Yelp’s filtering is reasonable and its filtering algorithm seems to be correlated with abnormal spamming behaviors.

Analyzing and Detecting Opinion Spam on a Large-scale Dataset via Temporal and Spatial Patterns

Although opinion spam (or fake review) detection has attracted significant research attention in recent years, the problem is far from solved. One key reason is that there is no large-scale ground truth labeled dataset available for model building. Some review hosting sites such as Yelp.com and Dianping.com have built fake review filtering systems to ensure the quality of their reviews, but their algorithms are trade secrets. Working with Dianping, we present the first large-scale analysis of restaurant reviews filtered by Dianping's fake review filtering system. Along with the analysis, we also propose some novel temporal and spatial features for supervised opinion spam detection. Our results show that these features significantly outperform existing state-of-art features.

Fake Review Detection Based on Joint Topic and Sentiment Pre-Training Model

Fake Review Detection Based on Joint Topic and Sentiment Pre-Training Model

Fake review detection on online E-commerce platforms: a systematic literature review

Fake review detection on online E-commerce platforms: a systematic literature review

Improved Fake Reviews Detection Model Based on Vertical Ensemble Tri-Training and Active Learning

People’s increasingly frequent online activity has generated a large number of reviews, whereas fake reviews can mislead users and harm their personal interests. In addition, it is not feasible to label reviews on a large scale because of the high cost of manual labeling. Therefore, to improve the detection performance by utilizing the unlabeled reviews, this article proposes a fake reviews detection model based on vertical ensemble tri-training and active learning (VETT-AL). The model combines the features of review text with the user behavior features as feature extraction. In the VETT-AL algorithm, the iterative process is divided into two parts: vertical integration within the group and horizontal integration among the groups. The intra-group integration is to integrate three original classifiers by using the previous iterative models of the classifiers. The inter-group integration is to adopt the active learning based on entropy to select the data with the highest confidence and label it, and as the result of that, the second generation classifiers are trained by the traditional process to improve the accuracy of the label. Experimental results show that the proposed model has a good classification performance.

Detection of Online Fake Reviews Based on Text Emotion

online groups offer clients with ways to overpower a few data hurdles and limitations, like the challenge to get self-governing data about movies and for the co-occurrence of positive and negative reactions within reviews. False reviews will disturb such choices because of misleading data, causing commercial disadvantages for the customers. Recognition of false opinions has thus expected very large concentration now days. But, many websites have only concentrated on handling the problematical comments and reviews. Our work tends to categorize people opinions into groups of true orfalse polarization by employing text feature analysis. In our work, our team analyze people opinions by implementing Sentiment Analysis techniques to recognize false opinions. Sentiment Analysis and text feature categorization techniques were used to a database containing people opinions. Furthermore, the estimation reviews acquired from reviewers could be categorized into good or bad opinions, that could be utilized by a customer to choose a movie. Further the proposed technique will graph based on the classification of true and fake reviews as the analysis of good and bad reviews for a product (movie). It will help us to predict the ratio of fake reviews to true reviews easily. To estimate the accomplishment of SA technique, this work has employed accurateness, exactness, recollection and F-degree as a performance rate.

Fake review and reviewer detection through behavioral graph partitioning integrating deep neural network

With a profound effect of online reviews on customers’ decisions about purchasing products or services, untruthful (fake) reviews written to deceive product quality and receive unfair commercial benefits have become a crucial problem. In this work, we propose a graph partitioning approach (BeGP) and its extension (BeGPX) to distinguish fake reviewers from benign ones. The main idea of BeGP is to first construct a behavioral graph in which reviewers are connected if they share common characteristic features that capture their similar behavior. Then, the algorithm starts with a small subgraph of known fake reviewers and afterwards repeatedly expands the subgraph by inducing other connected suspicious reviewers. Subsequently, all reviews of those suspects are hypothesized to be untruthful. Moreover, to enhance the performance of fake review(er) detection, BeGPX employs additional analysis of semantic content and emotions expressed in reviews. In particular, we use the deep neural network to learn word embeddings representation and lexicon-based emotion indicators in order to integrate into the graph construction process. We demonstrate the effectiveness of BeGP and BeGPX on two real-world review datasets from Yelp.com. The results show that both approaches outperform state-of-the-art methods with accurately identifying fake review(er)s within the k-first order of rankings. In addition, BeGPX shows significant enhancement although being provided with only a few amount of learning labeled data.

Development of Integrated Neural Network Model for Identification of Fake Reviews in E-Commerce Using Multidomain Datasets.

Online product reviews play a major role in the success or failure of an E-commerce business. Before procuring products or services, the shoppers usually go through the online reviews posted by previous customers to get recommendations of the details of products and make purchasing decisions. Nevertheless, it is possible to enhance or hamper specific E-business products by posting fake reviews, which can be written by persons called fraudsters. These reviews can cause financial loss to E-commerce businesses and misguide consumers to take the wrong decision to search for alternative products. Thus, developing a fake review detection system is ultimately required for E-commerce business. The proposed methodology has used four standard fake review datasets of multidomains include hotels, restaurants, Yelp, and Amazon. Further, preprocessing methods such as stopword removal, punctuation removal, and tokenization have performed as well as padding sequence method for making the input sequence has fixed length during training, validation, and testing the model. As this methodology uses different sizes of datasets, various input word-embedding matrices of n-gram features of the review's text are developed and created with help of word-embedding layer that is one component of the proposed model. Convolutional and max-pooling layers of the CNN technique are implemented for dimensionality reduction and feature extraction, respectively. Based on gate mechanisms, the LSTM layer is combined with the CNN technique for learning and handling the contextual information of n-gram features of the review's text. Finally, a sigmoid activation function as the last layer of the proposed model receives the input sequences from the previous layer and performs binary classification task of review text into fake or truthful. In this paper, the proposed CNN-LSTM model was evaluated in two types of experiments, in-domain and cross-domain experiments. For an in-domain experiment, the model is applied on each dataset individually, while in the case of a cross-domain experiment, all datasets are gathered and put into a single data frame and evaluated entirely. The testing results of the model in-domain experiment datasets were 77%, 85%, 86%, and 87% in the terms of accuracy for restaurant, hotel, Yelp, and Amazon datasets, respectively. Concerning the cross-domain experiment, the proposed model has attained 89% accuracy. Furthermore, comparative analysis of the results of in-domain experiments with existing approaches has been done based on accuracy metric and, it is observed that the proposed model outperformed the compared methods.

Fake reviews classification using deep learning ensemble of shallow convolutions

Online reviews have a decisive impact on consumers’ purchasing decisions. This opens the doors for spammers and scammers to post fake reviews for promoting non-existent products or undermine competitor products to affect social behavior. Thus, the identification of reviews as fake and real has become ever more important. Traditional approaches for text classification use a bag-of-words model to represent text which causes sparsity and word representations learnt from neural networks with limited ability to handle unknown words. In this paper, we propose a technique based on three different models trained on the idea of a multi-view learning technique and create an ensemble of all models by employing an aggregation technique for generating final predictions. The core idea of our methodology is to extract rich information from the text of reviews by combining bag-of-n-grams and parallel convolution neural networks(CNNs). By using an n-gram embedding layer with small kernel sizes we can use local context with the same computation power as required to train deep and complex CNNs. Our CNN-based architecture consumes n-gram embeddings as input and uses the parallel convolutional blocks to extract richer feature representations from text. Our approach for the detection of fake reviews also combines textual linguistic features and non-textual features related to reviewer behavior. We evaluate our approach on publically available Yelp Filtered Dataset and achieve F1 scores of up to 92% for classifying fake reviews.

From conflicts and confusion to doubts: Examining review inconsistency for fake review detection

Inconsistency in online consumer reviews (OCRs) may cause uncertainty and confusion to consumers when they make purchase decisions. However, there is a lack of a systematic and empirical investigation of review inconsistency in the literature. This research characterizes review inconsistency from multiple aspects, including rating-sentiment, content, and language, and proposes hypotheses about their effects on fake OCR detection by drawing upon deception and attitude-behavior consistency theories. We characterize review inconsistency with 22 features, and test the hypotheses with machine learning models developed for fake OCR detection. Our empirical evaluation results using real OCRs not only confirm the presence of review inconsistency, but also demonstrate significant positive effects of review inconsistency on the performance of fake OCR detection. The research findings have important implications for improving the effectiveness of consumer decision making and the trustworthiness of OCRs.

Resampling imbalanced data to detect fake reviews using machine learning classifiers and textual-based features

Fraudulent online sellers often collude with reviewers to garner fake reviews for their products. This act undermines the trust of buyers in product reviews, and potentially reduces the effectiveness of online markets. Being able to accurately detect fake reviews is, therefore, critical. In this study, we investigate several preprocessing and textual-based featuring methods along with machine learning classifiers, including single and ensemble models, to build a fake review detection system. Given the nature of product review data, where the number of fake reviews is far less than that of genuine reviews, we look into the results of each class in detail in addition to the overall results. We recognise from our preliminary analysis that, owing to imbalanced data, there is a high imbalance between the accuracies for different classes (e.g., 1.3% for the fake review class and 99.7% for the genuine review class), despite the overall accuracy looking promising (around 89.7%). We propose two dynamic random sampling techniques that are possible for textual-based featuring methods to solve this class imbalance problem. Our results indicate that both sampling techniques can improve the accuracy of the fake review class—for balanced datasets, the accuracies can be improved to a maximum of 84.5% and 75.6% for random under and over-sampling, respectively. However, the accuracies for genuine reviews decrease to 75% and 58.8% for random under and over-sampling, respectively. We also discover that, for smaller datasets, the Adaptive Boosting ensemble model outperforms other single classifiers; whereas, for larger datasets, the performance improvement from ensemble models is insignificant compared to the best results obtained by single classifiers.