A Survey on Fake Review Detection using Machine Learning Techniques

Online reviews significantly influence consumer purchase decisions and business reputations on digital platforms. However, the widespread presence of fake reviews not only misguides consumers but also undermines the reliability of online reviews. Therefore, detecting fake reviews is crucial for various stakeholders and has evolved from simple visual inspection to the use of advanced machine learning models. Despite the proven effectiveness of machine learning models in fake review detection, several key research gaps remain.First, most predictive models rely on binary classification (i.e., true vs. fake), which assumes that review authenticity is a clear-cut distinction between real and fake. However, online reviews often lie on a spectrum of deception, where subtle manipulation, exaggeration, and subjective bias blur the boundary between authenticity and fabrication. Second, prior research lacks a clearly structured framework that accounts for behavioural features in predicting deceptive reviews.To address these gaps, this study develops a probabilistic modelling framework that: 1) estimates the likelihood of deception on a continuous spectrum, allowing for more flexible and accurate detection beyond a rigid true/false label; 2) systematically organizes behavioural features into three dimensions – structural (e.g., number of friends), relational (e.g., number of compliments) and activity-based (e.g., review frequency), based on Social Capital Theory; 3) incorporates store-level attributes, such as average rating, number of reviews, and consumer-generated “vibes”.This study uses a dataset of 32,964 restaurant reviews from Yelp, covering both real and fake reviews from January 2005 to November 2024. A range of probabilistic machine models – including Logistic Regression, Decision Tree, Random Forest, XGBoost, and Artificial Neural Networks – are implemented and compared using 5-fold cross-validation. XGBoost is selected as the final model based on overall superior performance across Precision, Recall, F1-Score, Accuracy, and Area Under the ROC Curve (AUC).Results show that relational and structural behavioural features are among the top predictors. Interestingly, reviewers high in social capital features – such as elite reviewers (designated by Yelp as “elite” based on their activity, consistency, and perceived credibility) – are more likely to generate fake reviews. The average probability of fake review among elite reviewers is 33.5%, compared to 12% among non-elite reviewers. At the store level, reviews associated with high-rated businesses tend to exhibit higher probabilities of being fake. Furthermore, the distribution of fakeness probability across star ratings follows a U-shaped pattern, with reviews at 1-star and 5-star exhibiting higher probabilities of deception, and a secondary peak observed at 4-star.This study contributes to the literature by developing a systematic and behaviourally grounded probabilistic model to predict fake online reviews. Practically, detecting the probabilities of fake review enhances review transparency for consumers, protects brand reputation for businesses, and support fair review policies for regulators.

With the widespread of fake online reviews, the detection of fake reviews has become a hot research issue. Despite the efforts of existing studies on fake review detection, the issues of imbalanced data and feature pruning still lack sufficient attention. To address these gaps, the present study proposes an ensemble model for the detection of fake online reviews. The model consists of four steps, and the first three steps are proposed to optimize the base classifiers: (i) Data resampling: We propose a novel way to address the data imbalance problem by combining the resampling and the grid search technique. (ii) Feature pruning: We propose an ablation study to drop unimportant features. (iii) Parameters optimization: We apply the grid search algorithm to determine suitable values of the relevant parameters for each base classifier. (iv) Classifier ensembling: We apply majority voting and stacking strategies to integrate the optimized base classifiers. The proposed data resampling method is also applied for the meta-classifier in the stacking ensemble model. This study produces advances in terms of combining different methods or algorithms into a model and the results show that the proposed ensemble model outperforms some existing techniques, thereby providing a new way to solve the data imbalance and feature pruning issues in the field of fake review detection.

Nowadays, O2O commercial platforms are playing a crucial role in our daily purchases. However, some people are trying to manipulate the online market maliciously by opinion spamming, a kind of web fraud behavior like writing fake reviews, due to fame and profits, which will harm online purchasing environment and should be detected and eliminated. Moreover, manual fake reviewers are more deceptive compared with old web spambots. Although several efficient methods were proposed in the fake review detection field, the manual fake reviewers are also evolving rapidly. They imitate to be benign users to control the velocity of review fraud actions, and deceive the detection system. Our investigation presented that geolocation factor is potential and can well reflect the distinctions between fake reviewers and benign users. In this research, we analyzed the geolocations of shops in reviews, found the distinct distribution features of those in fake reviewers and benign users, and proposed a SpamTracer model that can identify fake reviewers and benign users by exploiting an improved HMM (Hidden Markov Model). Our experiment demonstrated that SpamTracer could achieve 71% accuracy and 76% recall in the unbalanced dataset, outperforming some excellent classical approaches in the aspect of stability. Furthermore, SpamTracer can help to analyze the regularities of review fraud actions. Those regularities reflect the time and location in which online shops are likely to hire fake reviewers to increase their turnover. We also found that a small group of fake reviewers tend to work with plural shops located in a small business zone.

Fake (deceptive) reviews have become a serious problem for online consumers, with the proliferation of online marketplaces leading to an increase in spurious reviews that are often used to lure or discourage potential customers. While sentiment analysis has been introduced to the e-commerce sector, the lack of an effective method to differentiate between authentic and fake reviews is still a major challenge. Existing approaches face issues such as slow convergence and inadequate precision. In order to address these challenges, this paper proposes a new approach that integrates sentiment features into the review detection process. The proposed approach uses a feature extraction method that utilizes a preconstructed sentiment dictionary, a pre-trained BERT model to extract feature vectors, and a fully connected dense layer to classify reviews as real or fake using the softMax function. The effectiveness of the proposed approach was evaluated on the Yelp dataset, showing a nearly 7% improvement in accuracy compared to existing feature sets and a nearly 4% improvement over existing state-of-the-art methods. The integration of sentiment features has shown promising results in detecting fake reviews, which is crucial for ensuring a fair and trustworthy online marketplace.

Consumers reviews on ecommerce websites, online services, ratings and experience stories are useful for the user as well as the vendor. The reviewer can increase their brand’s loyalty and help other customers understand their experience with the product. Similarly reviews help the vendors gain more profiles by increasing their sale of products, if consumers leave positive feedback on their product review. But unfortunately, these review mechanisms can be misused by vendors. For example, one may create fake positive reviews to promote brand’s reputation or try to demote competitor’s products by leaving fake negative reviews on their product. Existing solutions with supervised include application of different machine learning algorithms and different tools like Weka. Unlike the existing work, instead of using a constrained dataset I chose to have a wide variety of vocabulary to work on such as different subjects of datasets combined as one big data set. Sentiment analysis has been incorporated based on emojis and text content in the reviews. Fake reviews are detected and categorized. The testing results are obtained through the application of Naïve Bayes, Linear SVC, Support Vector Machine and Random forest algorithms. The implemented (proposed) solution is to classify these reviews into fake or genuine. The highest accuracy is obtained by using Naïve Bayes by including sentiment classifier.

The prevalence of fake reviews and ratings in online marketing has become a significant issue, undermining consumer trust and damaging business reputations. This study aims to identify the extent and impact of fake reviews and explore innovative strategies for traders to combat this problem and maintain authenticity. A mixed-method approach was adopted, including a survey of 100 respondents to gauge public awareness and perception of fake reviews. The findings highlight the critical need for advanced detection methods, increased transparency, and consumer education to foster trust in online platforms. Statistical analyses, including ANOVA and Chi-Square tests, were used to analyze the data. The survey revealed that 75% of respondents encounter fake reviews frequently, with 40% being highly aware of the issue. The impact of fake reviews on purchasing decisions is significant, affecting 80% of the respondents. To address this issue, traders can implement advanced AI algorithms, encourage genuine reviews through incentives, increase transparency through verification processes, and collaborate with review platforms to establish stricter monitoring systems. Additionally, educating consumers about identifying fake reviews and promoting ethical online behavior are crucial steps towards mitigating this issue. This study concludes that by adopting these innovative strategies, traders can protect their reputations, foster consumer trust, and ensure the authenticity of online reviews and ratings. Future research should focus on developing more sophisticated detection technologies and exploring the long-term effects of fake reviews on consumer behavior and market dynamics.

Online review plays a crucial role in many current e-commerce applications. However, fake reviews would mislead users. Therefore, detecting such reviews is an important task for safeguarding the interests of users. But the review sequence has been neglected by the former work. In this paper, we explore the issue on fake review detection in review sequence, which is crucial for implementing online anti-opinion spam. We first analyze the characteristics of fake reviews. Based on review contents and reviewer behaviors, six time sensitive features are proposed to find the fake reviews. And then, we devise two type of detection methods, the supervised and the threshold-based, for spotting the fake reviews as early as possible. Finally, we carry out intensive experiments on a real-world review set to verify the effectiveness of our methods. The experimental results show that our methods can identify the fake reviews orderly with high precision and recall.

Instruments of corporate risk and reputation assessment tools are quintessentially developed on structured quantitative data linked to financial ratios and macroeconomics. An emerging stream of studies has challenged this norm by demonstrating improved risk assessment and model prediction capabilities through unstructured textual corporate data. Fake online consumer reviews pose serious threats to a business’ competitiveness and sales performance, directly impacting revenue, market share, brand reputation and even survivability. Research has shown that as little as three negative reviews can lead to a potential loss of 59.2 % of customers. Amazon, as the largest e-commerce retail platform, hosts over 85,000 small-to-medium-size (SME) retailers (UK), selling over fifty percent of Amazon products worldwide. Despite Amazon's best efforts, fake reviews are a growing problem causing financial and reputational damage at a scale never seen before. While large corporations are better equipped to handle these problems more efficiently, SMEs become the biggest victims of these scam tactics. Following the principles of attribute (AA) and responsible (RA) analytics, we present a novel hybrid method for indexing enterprise risk that we call the Fake Review Index (RFRI). The proposed modular approach benefits from a combination of structured review metadata and semantic topic index derived from unstructured product reviews. We further apply LIME to develop a Confidence Score, demonstrating the importance of explainability and openness in contemporary analytics within the OR domain. Transparency, explainability and simplicity of our roadmap to a hybrid modular approach offers an attractive entry platform for practitioners and managers from the industry.

Detecting review spam is important for current e-commerce applications. However, the posted order of review has been neglected by the former work. In this paper, we explore the issue on fake review detection in review sequence, which is crucial for implementing online anti-opinion spam. We analyze the characteristics of fake reviews firstly. Based on review contents and reviewer behaviors, six time sensitive features are proposed to highlight the fake reviews. And then, we devise supervised solutions and a threshold-based solution to spot the fake reviews as early as possible. The experimental results show that our methods can identify the fake reviews orderly with high precision and recall.

Fake review detection and its elimination from the given dataset using different Natural Language Processing (NLP) techniques is important in several aspects. In this article, the fake review dataset is trained by applying two different Machine Learning (ML) models to predict the accuracy of how genuine are the reviews in a given dataset. The rate of fake reviews in E-commerce industry and even other platforms is increasing when depend on product reviews for the item found online on different websites and applications. The products of the company were trusted before making a purchase. So this fake review problem must be addressed so that these large E-commerce industries such as Flipkart, Amazon, etc. can rectify this issue so that the fake reviewers and spammers are eliminated to prevent users from losing trust on online shopping platforms. This model can be used by websites and applications with few thousands of users where it can predict the authenticity of the review based on which the website owners can take necessary action towards them. This model is developed using Naïve Bayes and random forest methods. By applying these models one can know the number of spam reviews on a website or application instantly. To counter such spammers, a sophisticated model is required in which a need to be trained on millions of reviews. In this work “amazon Yelp dataset” is used to train the models and its very small dataset is used for training on a very small scale and can be scaled to get high accuracy and flexibility.

Gaming the system: Fake online reviews v. consumer law

Online reviews significantly influence consumer behavior and business reputations. Detecting fake reviews is important for maintaining trust and integrity in these platforms. We present an aspect-based sentiment analysis approach, referred to as FakeDetectionGCN, to distinguish genuine feedback from deceptive content. The idea is to analyze sentiments related to specific aspects (features) within reviews. Graph convolutional networks are used to model the complex contextual dependencies in the review texts. Additionally, SenticNet, an external semantic resource, is integrated to enhance the understanding of sentiments in the reviews. This model is capable of identifying both human-generated (genuine) as well as computer-generated (fake) reviews. It has been evaluated on two types of datasets and has shown strong performance across both. Through this work, we contribute to the effective detection of fake reviews and maintaining a trustworthy online review ecosystem.

The proliferation of Artificial Intelligence (AI)-generated fake reviews poses an unprecedented threat to the integrity of e-commerce platforms, particularly in developing markets where regulatory frameworks remain nascent. This study proposes an adversarial transformer network framework specifically designed to detect sophisticated fake reviews on Indonesian e-commerce platforms. We developed a novel adversarial training architecture that pairs a Bidirectional Encoder Representations from Transformers (BERT)-based classifier model with a generator capable of producing human-like fake reviews, creating an iterative optimization process that enhances detection robustness. The scientific novelty of this work is threefold: (i) architectural innovation, through the integration of IndoBERT as a discriminator with a fine-tuned Generative Pre-trained Transformer (GPT)-based generator in a competitive adversarial loop; (ii) linguistic innovation, by embedding Indonesian-specific preprocessing (slang handling, code-mixed normalization, emoticon filtering) to address multilingual and culturally diverse contexts; and (iii) training innovation, by introducing gradient penalty mechanisms and iterative adversarial updates that enhance robustness against Large Language Model (LLM)-generated reviews. Together, these contributions distinguish our framework from prior adversarial Natural Language Processing (NLP) approaches that primarily focused on English-language data and lacked local linguistic customization. To the best of our knowledge, this represents the first adversarial transformer framework tailored for Indonesian e-commerce fake review detection. Using a comprehensive dataset of 50,000 authentic reviews collected from major Indonesian e-commerce platforms (Tokopedia and Shopee) and 25,000 AI-generated fake reviews, our methodology achieved significant improvements over traditional detection methods. The adversarial framework demonstrated superior performance with an accuracy of 94.3%, precision of 93.8%, recall of 94.7%, and F1-score of 94.2%, outperforming baseline BERT models by 8.7% in accuracy. Our approach addresses the critical challenge of detecting increasingly sophisticated AI-generated fake reviews while providing insights into the unique linguistic patterns of Indonesian online commerce discourse. The findings contribute to both the theoretical understanding of adversarial learning in NLP and practical applications for maintaining trust in digital marketplaces.

In e-commerce, user reviews can play a significant role in determining the revenue of an organisation. Online users rely on reviews before making decisions about any product and service. As such, the credibility of online reviews is crucial for businesses and can directly affect companies’ reputation and profitability. That is why some businesses are paying spammers to post fake reviews. These fake reviews exploit consumer purchasing decisions. Consequently, the techniques for detecting fake reviews have extensively been explored in the past twelve years. However, there still lacks a survey that can analyse and summarise the existing approaches. To bridge up the issue, this survey paper details the task of fake review detection, summing up the existing datasets and their collection methods. It analyses the existing feature extraction techniques. It also summarises and analyses the existing techniques critically to identify gaps based on two groups: traditional statistical machine learning and deep learning methods. Further, we conduct a benchmark study to investigate the performance of different neural network models and transformers that have not been used for fake review detection yet. The experimental results on two benchmark datasets show that RoBERTa performs about 7% better than the state-of-the-art methods in a mixed domain for the deception dataset with the highest accuracy of 91.2%, which can be used as a baseline for future studies. Finally, we highlight the current gaps in this research area and the possible future directions.

Ontology based sentiment analysis for fake review detection