Fake Online Reviews Research Articles

Survey on Fake Review Detection System

Abstract: In today's business landscape, online reviews play a crucial role in shaping commerce. A large portion of purchase decisions for online products is driven by customer feedback. Consequently, some individuals or groups try to manipulate product reviews to their advantage. Fake online reviews have a considerable effect on the experiences of online consumers, sellers, and e-commerce platforms. Although there has been academic research focused on identifying fake reviews, there is still a need for studies that thoroughly examine and summarize their origins and impacts. This work introduces a combination of semi-supervised and supervised text mining models to detect fake reviews, comparing their performance using datasets from reviews.

Designing a deep learning-based application for detecting fake online reviews

In the era of prevalent online commerce, online reviews significantly influence purchasing decisions. Unfortunately, this has also led to the emergence of fake reviews, which can deceive consumers and undermine trust in online platforms. Our study addresses this issue by developing DenyBERT, a deep learning-based software that enhances the Bidirectional Encoder Representations from Transformers (BERT) framework with Deep and Light Transformation (DeLighT) and Knowledge Distillation (KD) techniques. These innovations not only reduce computational demands but also improve the model's accuracy in identifying fake reviews, making it ideally suited for real-world applications. Significantly, DenyBERT requires only 16.01M parameters-significantly fewer than its predecessors such as BERT and TinyBERT-yet achieves a robust accuracy of 96.12% and an F1-score of 96.47%. This efficiency makes it particularly suited for deployment on devices with limited processing capabilities. The software, developed in Python, features a flexible input mechanism that allows for analyzing reviews directly from websites via URL or via manual input of review paragraphs. Our findings indicate that DenyBERT outperforms existing models in both speed and accuracy, making it a powerful tool for combating fake reviews in real-time scenarios. This advancement not only enhances user trust in online review systems but also supports e-commerce platforms in maintaining a fair and transparent market environment.

The impact of fake online reviews on customer satisfaction: an empirical study on JD.com

The impact of fake online reviews on customer satisfaction: an empirical study on JD.com

Hospitality customer intentions to write fake online reviews: A cross-cultural approach

This paper examines the antecedents and consequences of customer intentions to write fake online reviews on Agoda.com as a case in the hospitality context. Brand nostalgia, brand strength, moral attitude, review-related skepticism, and perceived unfairness were represented as antecedents of customer intentions, while boycott behavior, willingness to pay a price premium, and customer satisfaction were represented as consequences of their intentions. Data was gathered using a structured survey from 373 Italian, 440 French, and 392 British customers. Findings present significant insights into customer intentions to write fake online reviews. In addition, multi-group analysis highlights the differences among nationalities. This paper provides valuable insights for industry professionals and policymakers in the hospitality industry.

Detection of Fake Online Reviews Using Semi Supervised and Supervised Learning

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.

Fake Review Detection using BERT Transfer Learning Algorithm

Abstract: In this research, our main focus is on tackling the issue of fake online reviews, which has become increasingly prevalent due to the vast amount of content generated by users on various online platforms. These reviews have a big impact on what people decide to buy, emphasizing how important it is for them to be real and trustworthy. However, the rise in fake reviews has cast a shadow of doubt over the credibility of online platforms, making it imperative to find effective ways to discern the real from the fake. To address this challenge, we propose a strong model that utilizes the capabilities of advanced deep learning algorithms—BERT (Bidirectional Encoder Representations from Transformers) and Bidirectional Long Short-Term Memory Networks (BiLSTMs)—to accurately identify and filter out fake reviews. BERT excels in understanding the nuances of language and BiLSTMs effectively capture the order of words and phrases. Our plan involves training and validating this model using datasets sourced from reputable platform like Kaggle. By amalgamating these powerful algorithms and datasets, we aim to significantly enhance the accuracy and credibility of our fake review detection system. Ultimately, our goal is to restore consumer trust and empower individuals to make more informed choices in the expansive realm of online consumerism.

Incentivised dishonesty: Moral frameworks underlying fake online reviews

AbstractFeedback mechanisms, such as customer reviews and ratings, are essential for making informed decisions on online platforms, particularly in the presence of asymmetric information. However, the practice of reward‐based reviews is on the rise in online platforms, where sellers incentivise buyers to give biased feedback (e.g., 5‐star ratings) regardless of the quality of the products. This study intends to determine whether financial incentives motivate people to award dishonest ratings and explore the moral heuristics underlying this motivation. Using a hypothetical purchase scenario, responses were elicited from 411 participants and the Philosophical Moral Framework Measure (PMFM) was used to identify the moral frameworks that underlie the reported self‐interested behaviour. The findings reveal that the likelihood of giving fake reviews increases with an increase in financial incentives. The dominant moral framework of those who accepted the cashback offer is utilitarianism and egoism, whereas those who declined the offer primarily have deontology and virtue theory as dominant frameworks. The results also indicate that men and young individuals are more likely to give dishonest feedback. These findings not only advance the understanding of the interplay between financial incentives and self‐interested behaviour but also aid in identifying the moral frameworks underlying self‐interested behaviour.

SBiLM: Siamese Bi-LSTM model for handling imbalance in fake review detection

The growing significance of online reviews in e-commerce platforms has a profound impact on consumers' purchase decisions. Unfortunately, dishonest sellers exploit this system by engaging in deceptive practices and manipulating reviews. These fake reviews are very hard to be detected by humans. Hence, the issue of detecting fake online reviews has gained significant attention due to their prevalence. Typically, the datasets available have much higher number of real reviews as compared to fake reviews, which leads to data imbalance problem. Machine learning algorithms struggle to learn from these datasets and give biased results. However, existing studies on this topic have not adequately addressed the challenges posed by imbalanced data. They have mostly used under-sampling or over-sampling to handle imbalance in datasets, which leads to potential information loss or overfitting due to replication. Hence, to handle this class imbalance problem without using sampling techniques, this paper proposes a novel SBiLM model using Siamese Neural Network with Bidirectional LSTM and Manhattan Distance. SBiLM takes pair of reviews as inputs and computes similarity between them using distance metric. The outcomes indicate that the SBiLM model exhibits better performance in terms of both accuracy and loss, when compared with traditional deep learning models on a highly imbalanced restaurant review dataset. This presents a promising strategy for tackling the issues related to data imbalance in the domain of fake review detection.

The Illusion of Trust and the Paradox of Disclosure: How Fake Online Reviews of Physicians Manipulate Patient Choices and Exploit Privacy Boundaries

The Illusion of Trust and the Paradox of Disclosure: How Fake Online Reviews of Physicians Manipulate Patient Choices and Exploit Privacy Boundaries

Recognition of Phony Reviews in E-commerce Platform

Abstract: The business and commerce of today are greatly influenced by online reviews. The majority of how consumers choose which online products to buy is based on user reviews. As a result, opportunistic people or organizations try to slant product reviews in order to serve their own agendas. Now days, fake online reviews are more common, people simply post phony reviews to market their products, to cheat customers etc. In E-commerce application fake reviews are more common and we need a system to predict these fake reviews. Proposed system uses machine learning algorithm to identify the fake reviews in an Ecommerce platform. We build a new E-commerce application and customer registers themselves, browse and purchase the products. For the purchased products customers post reviews, and our system will predict the fake reviews using an algorithm.

Unmasking deception: a CNN and adaptive PSO approach to detecting fake online reviews.

Online reviews play a critical role in modern word-of-mouth communication, influencing consumers' shopping preferences and purchase decisions, and directly affecting a company's reputation and profitability. However, the credibility and authenticity of these reviews are often questioned due to the prevalence of fake online reviews that can mislead customers and harm e-commerce's credibility. These fake reviews are often difficult to identify and can lead to erroneous conclusions in user feedback analysis. This paper proposes a new approach to detect fake online reviews by combining convolutional neural network (CNN) and adaptive particle swarm optimization with natural language processing techniques. The approach uses datasets from popular online review platforms like Ott, Amazon, Yelp, TripAdvisor, and IMDb and applies feature selection techniques to select the most informative features. The paper suggests using attention mechanisms like bidirectional encoder representations from transformers and generative pre-trained transformer, as well as other techniques like Deep contextualized word representation, word2vec, GloVe, and fast Text, for feature extraction from online review datasets. The proposed method uses a multimodal approach based on a CNN architecture that combines text data to achieve a high accuracy rate of 99.4%. This outperforms traditional machine learning classifiers in terms of accuracy, recall, and F measure. The proposed approach has practical implications for consumers, manufacturers, and sellers in making informed product choices and decision-making processes, helping maintain the credibility of online consumer reviews. The proposed model shows excellent generalization abilities and outperforms conventional discrete and existing neural network benchmark models across multiple datasets. Moreover, it reduces the time complexity for both training and testing.

The more they know: Using transparent online communication to combat fake online reviews

Technological advances and shifts in consumer preference continue to further the critical roles that digital platforms and online word-of-mouth play in organizational success. Within this context, a key concern is the growing proliferation of fake online reviews, which mislead consumers and damage businesses’ reputations, resulting in additional platform maintenance expenditures to curb this problem. This article demonstrates that a successful avenue to turn these expenses into effective investments is to embrace a culture of transparency by effectively communicating the platforms’ actions online. To this end, we first provide evidence of the danger posed by fake reviews. Using data from Amazon.com and ReviewMeta, we show that reviews suspected as fake and deleted by Amazon’s algorithms are, counterintuitively, more likely to be perceived as helpful by consumers. In addition, two experiments reveal that including subtle messages into the review section of an online retailing website, messages that communicate a company’s efforts to remove fake reviews, can successfully improve both perceptions of consumer helpfulness and purchase intention. Finally, a four-stage framework, VIEW—verify, inform, explore, and watch—provides a roadmap for managers of online review platforms to combat the problem of fake reviews.

Suspicion of online product reviews as fake: Cues and consequences

Consumers rely on online reviews because they deem information from a third party to be more credible than promotional communications. Unfortunately, not all online reviews are legitimate. It is therefore critical for marketers to gain a better understanding of how fake online reviews affect consumer purchasing behavior and what cues consumers use in evaluating review veracity. The current research examines the effect of suspicious reviews on reviewer’s opinion valuation, consumer attitudes toward the brand and website, and purchasing. Then it identifies the specific cues that consumers use to evaluate whether a review is fake or credible.

Deep Learning Hybrid Approaches to Detect Fake Reviews and Ratings

Nowadays, online reviews and ratings are the most valuable source of word-of-mouth, voice-of-customer, and feedback, also customers can make purchasing decisions on what to buy, where to buy, and what to select. Genuine online reviews are becoming popular, but unfortunately, we have an issue that might only sometimes be unbiased or accurate. Because most of the reviews are fake reviews and ratings, these could mislead innocent customers and highly influence customers' purchasing decisions in the wrong manner. This paper's primary goal is to accurately detect fake reviews and what is the main difference between them. The secondary goal is to detect fake ratings and actual ratings-based reviews across the online platform, especially Amazon datasets. The Paper proposes two novel deep-learning Hybrid techniques: CNN-LSTM for detecting fake online reviews, and LSTM-RNN for detecting fake ratings in the e-commerce domain. Both Hybrid models can outperform and achieve better performance with the most advanced word embedding techniques, Glove, and One hot encoding techniques. As per the experimental results, the first technique efficiently detects fake online reviews with the highest prediction accuracy. The second hybrid model is better than the existing models that detect fake online ratings with the most excellent precision of 93.8%. The experimental research efficiently revealed that the CNN-LSTM and LSTM-RNN methods are more efficient and practicable and might be better suited for optimal results and maximizing the efficiency of fake online review detection .

Chatbots Can Help to Distinguish Fake Online Reviews

Chatbots Can Help to Distinguish Fake Online Reviews

Understanding online fake review production strategies

Extending the literature that has, thus far, mostly focused on the detection of fake online reviews, this paper explores a more fundamental yet hitherto-unanswered question: How do people go about creating fake reviews in the first place? To delve deeper, it further investigates the role of individuals’ cognitive style—the way one gathers, processes, structures, and applies information. While cognitive style was measured using a quantitative scale, a qualitative approach was adopted to explore fake review production strategies. Fifty participants imagined that they had been hired by a marketing agency to write fake reviews, completed the writing task, shared their experiences, and then filled out a cognitive style questionnaire. Writing fake reviews involved four stages: gathering information, assimilating information, drafting the fake review, and finalizing the fake review production. Through a cognitive lens, the paper uncovers three fake review production strategies and explains why someone would adopt a certain strategy.

ANALYSIS OF THE ONLINE PURCHASE BEHAVIOUR OF ROMANIANS

In recent decades, technological development has experienced significant acceleration, and smart devices are now widely available. Romanian e-commerce market, although ahead of countries like Greece, Portugal, Italy or Bulgaria, has still a long way to go before reaching its full potential. The purpose of this paper is to analyse the online shopping behaviour of Romanians. For this, we analyzed statistic data on internet access and online purchases and discussed the findings of an online purchase behaviour survey of 580 Romanian respondents. The main findings of the survey suggest that, while 64 percent of respondents prefer online shopping to the classic non-virtual shopping, the top three risks that worry potential online Romanian buyers are: fake online reviews, uncertain quality of goods, and unreliable match. 5G technologies, ultra-fast smart devices, lack of borders in online commerce are already present, so the future belongs to those who will know how to adapt and anticipate the needs of online shoppers.

Do online review readers react differently when exposed to credible versus fake online reviews?

Marketing research on online reviews has attempted to understand the antecedents and consequences of review manipulation. Building on the elaboration likelihood model (ELM), this study deploys a rare dataset that allows distinguishing credible from less credible (and likely fake) online reviews by means of the online review posting policy adopted by the movie review website Naver.com. We use text analysis entailing word embedding and topic modelling techniques such as Latent Dirichlet Allocation, to capture content depth across different types of online reviews (credible vs manipulated). Furthermore, we explore how differences in the textual content of credible vs manipulated online reviews affect customer purchase decisions. Our results highlight that less credible reviews tend to contain more superficial information compared to more credible reviews, and that different levels of source credibility lead to distinctively different impacts of online reviews on box office revenue.

Bell Pottinger And The Dark Art Of Public Relations

The spurious and unethical actions of the renowned global public relations (PR) firm Bell Pottinger in early 2017 cast a dark cloud over the PR industry in general. Aside from the economic and sociopolitical ramifications that emerged in the wake of this scandal, it has tainted the moral standing of all public relations professionals, including those in South Africa. There is little doubt that tactics such as offering to manipulate a client’s online reputation through the use of fake online accounts, newly created blog pages or fake online reviews are unethical, and take the industry back to a less glorious time in its history at a point when much emphasis is being placed on both ethics and values-based practice globally. Moral philosophy provides a basis for rationalising human motivation in decision making and action. However, it can be argued that there is potentially a mismatch between theories and moral frameworks created for individualistic cultures, and their application within communal cultures. Building social capital in any society begins with a commitment to support the collective interests of the community. Thus, any discussion of thevalue of ethical communication practice for society must begin with a concern for the nature and integrity of community. Against this background this article utilises the Bell Pottinger case study to examine the tensions that arise between individual values and communal PR practice, and to explore the moral implications of ethical PR practice in a communal context such as South Africa.

Detection of Fake Online Reviews using Semi-supervised and Supervised learning

Abstract: Nowadays, when somebody wants to make some decisions about a product or a service everyone goes with the reviews as it has become an essential part of decision making. When a customer wants to order a product on an e commerce website firstly everyone checks the review section in detail and further proceeds for decision making about the product. If the reviews posted were satisfactory for the customer he may order the product thus reviews become a reputed parameter for the businesses and companies and also a great source of information for the customers. Every customer thinks that the reviews he/she is seeing is authentic and any manipulation in that from any individuals or any rival companies which may lead to fake data which will be labeled as fake reviews. This type of attempt if not noticed may let us think about the gen-unity of the data. So these reviews are the most important parameter for the businesses and companies. There exist some groups or persons who make use of these reviews to forge customers for their own interest or damage their competitors reputation. In order to solve this problem we uses Machine learning techniques(Supervised and semi-supervised) to detect whether the given review is fake or not with high accuracy. Along with this objective we also focus on developing models which need less data to train.Since we can’t always be able to get labeled data we use semi-supervised machine learning to make use of unlabeled data.It is understandable our model should be capable of giving results in reasonably less time. .In this paper we proposed many classification algorithm like Support Vector Machine algorithm (SVM) , Random Forest algorithm (RF) and deep neural network