Spam Reviews Research Articles

Detecting review spammer groups based on generative adversarial networks

The detection of spammer groups has recently gained more attention. However, the existing spammer group detection approaches rely on manual feature engineering to design spam indicators or extract features to capture the aggregated behavioral patterns exhibited by spammer groups. This is costly and time-consuming. To address this limitation, we formulate spammer group detection as a problem of finding distribution differences between normal user groups and spammer groups, and propose a review spammer group detection approach based on generative adversarial networks. First, we perform multiview sequence sampling on the dataset and utilize the Word2Vec model to obtain low-dimensional vector representations of users. Second, we construct the N-nearest neighbor user relationship graph according to the vector similarities in the embedding space. In the closed neighborhood of each node, we use the DBSCAN algorithm to find candidate groups. Finally, we construct a generative adversarial network model for spammer group detection, which uses the sum of generator reconstruction loss and discriminator loss to evaluate the spamicities of candidate groups. The experimental results on three real-world review datasets indicate that the proposed approach outperforms the baseline approaches in detection performance.

Co-attention Based Feature Fusion Network for Spam Review Detection on Douban

Co-attention Based Feature Fusion Network for Spam Review Detection on Douban

Online Spam Review Detection: A Survey of Literature

The increasingly developed online platform generates a large amount of online reviews every moment, e.g., Yelp and Amazon. Consumers gradually develop the habit of reading previous reviews before making a decision of buying or choosing various products. Online reviews play an vital part in determining consumers’ purchase choices in e-commerce, yet many online reviews are intentionally created to confuse or mislead potential consumers. Moreover, driven by product reputations and merchants’ profits, more and more spam reviews were inserted into online platform. This kind of reviews can be positive, negative or neutral, but they had common features: misleading consumers or damaging reputations. In the past decade, many people conducted research on detecting spam reviews using statistical or deep learning method with various datasets. In view of that, this article first introduces the task of spam online reviews detection and makes a common definition of spam reviews. Then, we comprehensively conclude the existing method and available datasets. Third, we summarize the existing network-based approaches in dealing with this task and propose some direction for future research.

Fitness-Based Grey Wolf Optimizer Clustering Method for Spam Review Detection

Customers nowadays rely heavily on online reviews when making buying decisions. Various internet websites, including Amazon, Yelp, Google Plus, BookMyShow, Facebook, Twitter, and others, allow users to generate massive amounts of data. The information is gathered through feedback/reviews, comments, and tweets. Companies can leverage this information to improve the quality of their products. Spam reviews are created pretentiously by some businesses and people to promote or degrade the popularity of any product, organization, or person due to their reliance on these online reviews. Thus, identifying spam or nonspam review by the naked eye is nearly impossible. Classifying the reviews manually is also highly speculative. Hence, to overcome this issue, a fitness-based Grey Wolf Optimizer (FGWOK) clustering method is proposed in this paper to identify spam reviews. The fitness-based grey wolf optimization (GWO) is used to obtain the optimal cluster heads in the proposed method. In the fitness-based GWO, the position of the grey wolves is updated in two phases. In the first phase, all the search agents update their position using the contemporary GWO, and in the second phase, the fitness is evaluated to update the position. To prove that the proposed strategy is effective, three spam data sets, namely synthetic spam reviews, movie reviews, and Yelp hotel and restaurant reviews, have been used in our work. The reported results are compared with the existing state-of-art metaheuristic clustering methods like a genetic algorithm (GA), differential evolution (DE), particle swarm optimization (PSO), cuckoo search (CS), k-Means, and artificial bee colony clustering (ABCK) method. The experimental and statistical analysis results show that the proposed FGWOK algorithm outperforms current methodologies.

Detection of spam reviews using hybrid grey wolf optimizer clustering method

Detection of spam reviews using hybrid grey wolf optimizer clustering method

EUPHORIA: A neural multi-view approach to combine content and behavioral features in review spam detection

Nowadays, online reviews are the main source to customer opinions. They are especially important in the realm of e-commerce, where reviews regarding products and services influence the purchase decisions of customers, as well as the reputation of the commerce websites. Unfortunately, not all the online reviews are truthful and trustworthy. Therefore, it is crucial to develop machine learning techniques to detect review spam. This study describes EUPHORIA — a novel classification approach to distinguish spam from truthful reviews. This approach couples multi-view learning to deep learning, in order to gain accuracy by accounting for the variety of information possibly associated with both the reviews’ content and the reviewers’ behavior. Experiments carried out on two real review datasets from Yelp.com – Hotel and Restaurant – show that the use of multi-view learning can improve the performance of a deep learning classifier trained for review spam detection. In particular, the proposed approach achieves AUC-ROC equal to 0.813 and 0.708 in Hotel and Restaurant, respectively.

Spam Reviews Detection in the Time of COVID-19 Pandemic: Background, Definitions, Methods and Literature Analysis

During the recent COVID-19 pandemic, people were forced to stay at home to protect their own and others’ lives. As a result, remote technology is being considered more in all aspects of life. One important example of this is online reviews, where the number of reviews increased promptly in the last two years according to Statista and Rize reports. People started to depend more on these reviews as a result of the mandatory physical distance employed in all countries. With no one speaking to about products and services feedback. Reading and posting online reviews becomes an important part of discussion and decision-making, especially for individuals and organizations. However, the growth of online reviews usage also provoked an increase in spam reviews. Spam reviews can be identified as fraud, malicious and fake reviews written for the purpose of profit or publicity. A number of spam detection methods have been proposed to solve this problem. As part of this study, we outline the concepts and detection methods of spam reviews, along with their implications in the environment of online reviews. The study addresses all the spam reviews detection studies for the years 2020 and 2021. In other words, we analyze and examine all works presented during the COVID-19 situation. Then, highlight the differences between the works before and after the pandemic in terms of reviews behavior and research findings. Furthermore, nine different detection approaches have been classified in order to investigate their specific advantages, limitations, and ways to improve their performance. Additionally, a literature analysis, discussion, and future directions were also presented.

Assessing and Enhancing Adversarial Robustness of Predictive Analytics: An Empirically Tested Design Framework

ABSTRACT As predictive analytics increasingly applies supervised machine learning (SML) models to inform mission-critical decision-making, adversaries become incentivized to exploit the vulnerabilities of these SML models and mislead predictive analytics into erroneous decisions. Due to the limited understanding and awareness of such adversarial attacks, the predictive analytics knowledge and deployment need a principled technique for adversarial robustness assessment and enhancement. In this research, we leverage the technology threat avoidance theory as the kernel theory and propose a research framework for assessing and enhancing the adversarial robustness of predictive analytics applications. We instantiate the proposed framework by developing a robust text classification system, the ARText system. The proposed system is rigorously evaluated in comparison with benchmark methods on two tasks extensively enabled by SML: spam review detection and spam email detection, which then confirmed the utility and effectiveness of our ARText system. Results from numerous experiments revealed that our proposed framework could significantly enhance the adversarial robustness of predictive analytics applications.

AI tools for debunking online spam reviews? Trust of younger and older adults in AI detection criteria

ABSTRACT In order to make AI tools for spam review detection to be more trustworthy, two types of explanation were designed, the Text-AI tool and the Behaviour-AI tool. The Text-AI tool establishes detection criteria based on the textual features of reviews, while the Behaviour-AI tool establishes detection criteria based on the behavioural features of reviewers. The trust of younger (20–26 years) and older (50–78 years) adults in AI tools and the changes in credibility judgments for reviews and overall attitude toward the product made by them based on AI tools’ detection results were measured. We mainly found that: (i) Almost all the older participants reported that they trust AI tools’ prediction, but 48.7% of them would abandon AI when AI’s prediction was different from their own judgment. (ii) Younger adults showed a higher trust in the Behaviour-AI tool than in the Text-AI tool, especially when the AI tool detected more spam reviews than themselves. (iii) Regardless of age and types of explanation, participants perceived AI tools as more competent and benevolent when AI tools outperformed participants by detecting unexpected spam reviews.

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.

Hybrid ensemble and soft computing approaches for review spam detection on different spam datasets

Online customer reviews play an important influence in a client's choice to purchase an item and are seen as a significant source of knowledge that can be used to foresee public opinion when making purchase or commodity from an online store. These opinions are frequently manipulated by people who haven't been registered on the websites or who are paid by other organisations to create negative or misleading reviews about an item or brand. Spam reviews are generally fraudulent reviews, and they can have a significant impact on the digital marketplace's behaviour. With the growing need to convert such facts into usable evidence and knowledge, information retrieval and data mining have gotten a lot of attention. The modelling of documents into a clear and accurate set of characteristic single and numerous word phrases, which has an impact on overall actions and achievements, is predicted to be a key problem in natural language processing (NLP) known as feature extraction process. Quite a few kinds of features could be used to perform different tasks through various feature collection methods such as: Text categorization (Bag of words), Linguistic characteristics (LIWC), Genre Identification (POS tagging), Sentimental feature extraction, Term frequencies (TFIDF) and Word2Vec. For traditional classification tasks with smaller datasets, machine learning algorithms have produced the greatest results. Soft computing techniques, on the other hand, when optimised with larger datasets, provide a better solution for real-world scenario problems. This work is organised into several sections, each of which examines a distinct feature selection method, machine ensemble learning, and soft computing approaches in depth. Finally, the hybrid approach for detecting review spam is introduced.

Are Neighbors Alike? A Semi-supervised Probabilistic Ensemble for Online Review Spammers Detection

Are Neighbors Alike? A Semi-supervised Probabilistic Ensemble for Online Review Spammers Detection

User-based network embedding for opinion spammer detection

Due to the huge commercial interests behind online reviews, a tremendous amount of spammers manufacture spam reviews for product reputation manipulation. To further enhance the influence of spam reviews, spammers often collaboratively post spam reviews within a short period of time, the activities of whom are called collective opinion spam campaign. The goals and members of the spam campaign activities change frequently, and some spammers also imitate normal purchases to conceal the identity, which makes the spammer detection challenging. In this paper, we propose an unsupervised network embedding-based approach to jointly exploiting different types of relations, e.g., direct common behavior relation, and indirect co-reviewed relation to effectively represent the relevances of users for detecting the collective opinion spammers. The average improvements of our method over the state-of-the-art solutions on dataset AmazonCn and YelpHotel are [14.09%,12.04%] and [16.25%,12.78%] in terms of AP and AUC, respectively.

Application Of Machine Learning Techniques For Fake Customer Review Detection

Now-a-days with the increasing demand of the web , online marketing is additionally becoming progressively popular. This is often because; tons of products and services are easily available online. Hence, reviews of these products and services are vital for customers also as sellers. But, to gain profit or promotion, scammers produce fake reviews. These fake reviews written by scammers prevent customers and sellers reaching actual opinion about the products. Hence, fake reviews or spam reviews must be detected and eliminated so as to prevent misleading potential customers. In our work, supervised and semi supervised learning techniques are applied to detect spam review.

Detecting Arabic Spam Reviews in Social Networks Based on Classification Algorithms

Reviews or comments that users leave on social media have great importance for companies and business entities. New product ideas can be evaluated based on customer reactions. However, this use of social media is complicated by those who post spam on social media in the form of reviews and comments. Designing methodologies to automatically detect and block social media spam is complicated by the fact that spammers continuously develop new ways to leave their spam comments. Researchers have proposed several methods to detect English spam reviews. However, few studies have been conducted to detect Arabic spam reviews. This article proposes a keyword-based method for detecting Arabic spam reviews. Keywords or Features are subsets of words from the original text that are labelled as important. A term's weight, Term Frequency–Inverse Document Frequency (TF-IDF) matrix, and filter methods (such as information gain, chi-squared, deviation, correlation, and uncertainty) have been used to extract keywords from Arabic text. The method proposed in this article detects Arabic spam in Facebook comments. The dataset consists of 3,000 Arabic comments extracted from Facebook pages. Four different machine learning algorithms are used in the detection process, including C4.5, kNN, SVM, and Naïve Bayes classifiers. The results show that the Decision Tree classifier outperforms the other classification algorithms, with a detection accuracy of 92.63%.

Advances in spam detection for email spam, web spam, social network spam, and review spam: ML-based and nature-inspired-based techniques

Despite the great advances in spam detection, spam remains a major problem that has affected the global economy enormously. Spam attacks are popularly perpetrated through different digital platforms with a large electronic audience, such as emails, microblogging websites (e.g. Twitter), social networks (e.g. Facebook), and review sites (e.g. Amazon). Different spam detection solutions have been proposed in the literature, however, Machine Learning (ML) based solutions are one of the most effective. Nevertheless, most ML algorithms have computational complexity problem, thus some studies introduced Nature Inspired (NI) algorithms to further improve the speed and generalization performance of ML algorithms. This study presents a survey of recent ML-based and NI-based spam detection techniques to empower the research community with information that is suitable for designing effective spam filtering systems for emails, social networks, microblogging, and review websites. The recent success and prevalence of deep learning show that it can be used to solve spam detection problems. Moreover, the availability of large-scale spam datasets makes deep learning and big data solutions (such as Mahout) very suitable for spam detection. Few studies explored deep learning algorithms and big data solutions for spam detection. Besides, most of the datasets used in the literature are either small or synthetically created. Therefore, future studies can consider exploring big data solutions, big datasets, and deep learning algorithms for building efficient spam detection techniques.

Exploiting Burstiness in Reviews for Review Spammer Detection

Online product reviews have become an important source of user opinions. Due to profit or fame, imposters have been writing deceptive or fake reviews to promote and/or to demote some target products or services. Such imposters are called review spammers. In the past few years, several approaches have been proposed to deal with the problem. In this work, we take a different approach, which exploits the burstiness nature of reviews to identify review spammers. Bursts of reviews can be either due to sudden popularity of products or spam attacks. Reviewers and reviews appearing in a burst are often related in the sense that spammers tend to work with other spammers and genuine reviewers tend to appear together with other genuine reviewers. This paves the way for us to build a network of reviewers appearing in different bursts. We then model reviewers and their co-occurrence in bursts as a Markov Random Field (MRF), and employ the Loopy Belief Propagation (LBP) method to infer whether a reviewer is a spammer or not in the graph. We also propose several features and employ feature induced message passing in the LBP framework for network inference. We further propose a novel evaluation method to evaluate the detected spammers automatically using supervised classification of their reviews. Additionally, we employ domain experts to perform a human evaluation of the identified spammers and non-spammers. Both the classification result and human evaluation result show that the proposed method outperforms strong baselines, which demonstrate the effectiveness of the method.

Detection of spam reviews through a hierarchical attention architecture with N-gram CNN and Bi-LSTM

Spam reviews misguide decision makings of consumers and may seriously affect fair trading in the online markets. Existing methods for detecting spam reviews mainly focus on feature designs from linguistic and psychological clues, but they hardly reveal the potential semantics. Recent research works apply deep learning to capture semantics features, while these models fail to extract multi-granularity information of the text structures nor consider the mutual influence among the sentences. We propose a hierarchical attention network in which distinct attentions are purposely used at the two layers to capture important, comprehensive, and multi-granularity semantic information. At the first layer, we especially use an N-gram CNN to extract the multi-granularity semantics of the sentences. We then use a combination of convolution structure and Bi-LSTM to extract important and comprehensive semantics in a document at the second layer. Extensive experiments on public datasets demonstrate that our model has superior detection performance over the state-of-the-art baselines, improving F1 score in the mixed-domain to 89.3% (with 4.8 points absolute improvement), F1 score in the Doctor domain to 92.8% (with 9.9 points absolute improvement), F1 score in the Hotel domain to 86.1% (with 2.4 points absolute improvement) and F1 score in the cross-domain to 84.7% (with 10.4 points absolute improvement).

Survey on Spam Review Detection Using Spam Filtering Algorithms

Generally the people trust on product on the basis of that product reviews and rating. Reviews can affect an organization or profile of a brand. The corporation has to assess market reactions towards its goods. However, it is not straightforward to track and organize popular reviews. Many public views are hard to manually process in social media. A methodology is then required to categories positive or negative public assessments automatically. Online feedback will provide customers with an insight into the consistency, efficiency and advice of the product; this provides prospective buyers with a better understanding of the product. One such unrealized opportunity is the usability of web assessments from suppliers in order to fulfill client requirements by evaluating beneficial feedback. Good and negative reviews play a major role in assessing customer needs and in quicker collection of product input from consumers. Sentiment Analysis is a computer study that extracts contextual data from the text. In this study a vast number of online mobile telephone ratings are analyzed. We classify the text as positive and negative, but we also included feelings of frustration, expectation, disgust, apprehension, happiness, regret, surprise and confidence for spam review detection. This delimited grouping of feedback helps to holistically assess the product, allowing buyers to decide better.

Memetic Spider Monkey Optimization for Spam Review Detection Problem.

Spider monkey optimization (SMO) algorithm imitates the spider monkey's fission-fusion social behavior. It is evident through literature that the SMO is a competitive swarm-based algorithm that is used to solve difficult real-life problems. The SMO's search process is a little bit biased by the random component that drives it with high explorative searching steps. A hybridized SMO with a memetic search to improve the local search ability of SMO is proposed here. The newly developed strategy is titled Memetic SMO (MeSMO). Further, the proposed MeSMO-based clustering approach is applied to solve a big data problem, namely, the spam review detection problem. A customer usually makes decisions to purchase something or make an image of someone based on online reviews. Therefore, there is a good chance that the individuals or companies may write spam reviews to upgrade or degrade the stature or value of a trader/product/company. Therefore, an efficient spam detection algorithm, MeSMO, is proposed and tested over four complex spam datasets. The reported results of MeSMO are compared with the outcomes obtained from the six state-of-art strategies. A comparative analysis of the results proved that MeSMO is a good technique to solve the spam review detection problem and improved precision by 3.68%.