Academia.eduAcademia.edu

Outline

Title
Abstract
Figures
Introduction
Review Mining Task
Techniques of Spam Review Detection
Traditional Statistical Methods
Graph-Based Methods
Data Resource
Conclusion and Future Work
References

Online Spam Review Detection: A Survey of Literature

Profile image of Guandong XuGuandong Xu

Human-Centric Intelligent Systems

https://doi.org/10.1007/S44230-022-00001-3
visibility

…

description

17 pages

link

1 file

Abstract

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 comprehen...

Figures (12)
Fig. 1 Distribution of Focused Research Works. Review Mining Task takes the percentage of 17%, end-to-end classification task is 22%, and cold-start problems have the same proportion as classification task. Spammer detection task takes the percentage of 39%
Fig. 1 Distribution of Focused Research Works. Review Mining Task takes the percentage of 17%, end-to-end classification task is 22%, and cold-start problems have the same proportion as classification task. Spammer detection task takes the percentage of 39%
Table 1 Description of features in CATS Multicriteria Decision: Viviani et al. [20] used a multicrite- ria choice making approach based both on the evaluation of numerous criteria and the utilize of accumulation adminis- trators with the point of getting a veracity score related with each review. Based on this score, it is conceivable to identify spam reviews [20]. Specifically, they provide a definition of aggregation operator F:
Table 1 Description of features in CATS Multicriteria Decision: Viviani et al. [20] used a multicrite- ria choice making approach based both on the evaluation of numerous criteria and the utilize of accumulation adminis- trators with the point of getting a veracity score related with each review. Based on this score, it is conceivable to identify spam reviews [20]. Specifically, they provide a definition of aggregation operator F:
Fig. 2 Wang et al., model overview. They take the products items as the head part of the TransE network in their model, take the reviewers as the translation (relation) part and take the review as the tail part
Fig. 2 Wang et al., model overview. They take the products items as the head part of the TransE network in their model, take the reviewers as the translation (relation) part and take the review as the tail part
Fig. 3 Li et al., model overview. The embedding network consists four parts: user embedding layers, item embedding layers, review embedding networks, and rating embedding layers
Fig. 3 Li et al., model overview. The embedding network consists four parts: user embedding layers, item embedding layers, review embedding networks, and rating embedding layers
Table 2 Mukherjee et al. indicators
Table 2 Mukherjee et al. indicators
Fig.4 Xie et al., model overview. Relationship of Spammers. Reviewers and Customers
Fig.4 Xie et al., model overview. Relationship of Spammers. Reviewers and Customers
Fig.5 Yang et al., WMUSVM Algorithm Overview. This demon- strate builds up hypersphere with greatest volume, containing all beguiling reviews information, and all genuine reviews information are exterior of this hypersphere
Fig.5 Yang et al., WMUSVM Algorithm Overview. This demon- strate builds up hypersphere with greatest volume, containing all beguiling reviews information, and all genuine reviews information are exterior of this hypersphere
Fig.6 Nayak et al., review indicator framework. They demonstrate the review spamicity expectation as a two-class classification issue. The review spamicity pointer was built utilizing stacked LSTM mod- els and show yields the individual probabilities of each review being genuine or fakes
Fig.6 Nayak et al., review indicator framework. They demonstrate the review spamicity expectation as a two-class classification issue. The review spamicity pointer was built utilizing stacked LSTM mod- els and show yields the individual probabilities of each review being genuine or fakes
Table 4 Op_spam_v1.4 Datasets statistics
Table 4 Op_spam_v1.4 Datasets statistics
Table 6 Review datasets in Yelp.com
Table 6 Review datasets in Yelp.com
“Industry manufactured products like electronics, computers, etc. Table 5 Various features of different categories of products
“Industry manufactured products like electronics, computers, etc. Table 5 Various features of different categories of products
Table 7 Statistics of the 500 restaurants in Shanghai
Table 7 Statistics of the 500 restaurants in Shanghai

Related papers

IRJET- Spam Review Detection with Sentiment Analysis
IRJET Journal

IRJET, 2020

Product analysis is valuable for the upcoming buyers in order to help them to take decisions. To the end, different opinion approaches have been proposed, where deciding a review whether positive or negative is one of their key challenges. Recently, deep learning has emerged as an effective means of foe solving sentiment classification problems. A neural network inherently learns a useful portrayal that reacts without the intention of human efforts. However, the success of deep learning highly relies on the availability of wide-ranging training data. We propose a novel deep learning framework for evaluating the product through sentiment classification which employs prevalently available ratings as weak supervision signals. The framework consists of two steps: (1) learning a foremost depiction (an embedding space) which provides out the overall sentiment distribution of sentences through rating information; (2) adding a classification layer on top of the embedding layer and use labeled sentences for supervised fine-tuning. We explore two kinds of low-level network structure for modeling review sentences, namely, complex feature extractors and long short-term memory. To assess the advance framework, we set up a dataset containing a million weakly labeled review sentences and 11,754 labeled review sentences from various websites. Experimental results show the efficacy of the proposed framework and its superiority over baselines.

View PDFchevron_right
A Survey Based on Review Spam Detection and Its Techniques
Dr. Mithilesh Dubey

2020

Reviews that are displayed online is a key position in customers choice to buy an item or facilities. They are vital and worthy source of information that can be used to evaluate public suggestions / points of view regarding items or services. Due to its influence, producers and distributors are deeply worried with its inputs or reviews / opinions from customers. Such opinions are based solely on either consumer or reviewer's feelings or perceptions, thereby giving rise to potential concerns that wrongdoer may generate bogus reviews to unfairly support or bring down the reputation of an item or services. As false reviews become more common on the web and can be an issue to it. These fake reviews are called as spams. A method for distinguishing between truthful and untruthful reviews is therefore necessary. This article deals with highly machine learning techniques that are put forward to address problems of spams and evaluate the performance of various approaches used for classi...

View PDFchevron_right
A SURVEY OF FAKE/SPAM CUSTOMER OPINIONS DETECTION IN ECOMMERCE SITES
MAYSARA M B ALSAAD

JOURNAL OF HARBIN INSTITUTE OF TECHNOLOGY, 2022

User-generated reviews can have a substantial impact on an organization's income in e-commerce. When making a purchase or deciding on a service or product, online customers depend on the opinions of others. Thus, e-commerce product reviews' trustworthiness is critical for organizations, and it can have a direct impact on their reputation and revenue. As a result, some online purchasing and selling companies employ fraudsters to create bogus or fake opinions or reviews on their websites. The objective of fake reviews is to mislead customers into making the wrong purchasing decision. In the last two decades, different methods of detecting fraudulent reviews have been intensively investigated. However, there is still a lack of the literature surveys that can really investigate and summaries the current methods and challenges facing fake opinions detection. In order to tackle this problem, this survey sums up the publicly available datasets and their gathering methods for the detection of fraudulent reviews. It examines the methods that are currently in use for feature engineering for fake review analysis, as well as deep learning and classical machine learning that have been implemented for fake review classification and finds any inconsistencies and limitations.

View PDFchevron_right
Degree Thesis in Microdata Analysis Level : Master of Science ( MSc ) in Business Intelligence Detecting Fake Reviews with Machine Learning
Marina Uchoa

Many individuals and businesses make decisions based on freely and easily accessible online reviews. This provides incentives for the dissemination of fake reviews, which aim to deceive the reader into having undeserved positive or negative opinions about an establishment or service. With that in mind, this work proposes machine learning applications to detect fake online reviews from hotel, restaurant and doctor domains. In order to filter these deceptive reviews, Neural Networks and Support Vector Machines are used. Both algorithms’ parameters are optimized during training. Parameters that result in the highest accuracy for each data and feature set combination are selected for testing. As input features for both machine learning applications, unigrams, bigrams and the combination of both are used. The advantage of the proposed approach is that the models are simple yet yield results comparable with those found in the literature using more complex models. The highest accuracy achi...

View PDFchevron_right
Fake Review Detection on Using Machine Learning on Online Product Selling Platform
IJRASET Publication

International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2022

The increasing popularity of online review systems motivates malevolent intent in competing sellers and service providers to manipulate consumers by fabricating product/service reviews. Immoral actors use Sybil accounts, Bot farms, and purchase authentic accounts to promote products and vilify competitors. Facing the continuous advancement of review spamming techniques, more research work is been carried out to assess the approaches explored to date to combat fake reviews, and regroup to define new ones. Fake reviews detection attracts many researchers' attention due to the negative impacts on the society. Most existing fake reviews detection approaches mainly focus on semantic analysis of review's contents. This project is aimed at fake review detection in online platform, to prevent damage due to deceptive reviews.We propose a Novel Fake Reviews Detection based on Logistic Regression technique.

View PDFchevron_right
Netspam: Detection of Spam for Reviews in Online
Jyoti Neeli

2020

Today’s world people rely on available content in online social media, The probability that anybody can leave a review which provides a golden opportunity for spammers to write spam reviews on products and services. Identifying these spams and spammers has become a hot topic of research, but even though they have put forth so many methodologies, which will barely detect the spam reviews, but so forth none of these methodologies have shown the importance of these extracted features. In this work, a study proposes a framework, named Netspam, which is a novel based. The work utilizes spam features in order to model review datasets as a heterogeneous information network to map spam detection procedure into a classification problem. Using the importance of spam features help us to obtain better results in terms of different metrics experimented on real-world review dataset from Yelp and Amazon. Keywords—Netspam, Heterogeneous Information Network, Training data, Data mining, behavioral pa...

View PDFchevron_right
Review Spam Detection using Sentiments and Novel Features
Khalid Iqbal, Journal of Computer Science IJCSIS

Online websites reviews play an important role in todays electronic shopping. Review forums like Amazon help customers to interpret critiques about the product. Customers use review forums to check actual specification and quality of the product. Unfortunately, spammers often exploit these forums by generating spam like giving false reviews or advertising some other product. Spam review identification is becoming the upcoming area to focus as spammer may exploit the availability of these online review forums to misguide other users. It is vital to filter out fake reviews, providing users with relevant and true feedback and suggestions in the form of genuine reviews. In this paper, an efficient review spam detection framework is presented based on the link (page rank) and content based approach along with quality dependent features. Experiments have been performed on Amazon dataset. Results of Kendals, Spearmans and Osim correlation have shown that the proposed technique has outperformed the state-of-the-art methods and is more sensitive to detect spam.

View PDFchevron_right
Studying the Effectiveness of Supervised Classification Algorithms in Detecting Fake Online Reviews
International Res Jour Managt Socio Human

isara solutions, 2022

In this era of digitization Direct-to-Consumer (D2C) is a fast-track retail model which helps businesses sell items directly to clienteles via an online storefront, evading the chain of market intermediaries. The potential customers tend to make purchase decision according to the online reviews of the products. However, driven by profit, spammers post fake reviews to mislead the customers by promoting or demoting target product or services offered online. As there is no mechanism to control the reviews posted, anybody can write anything pseudonymously which conclusively leads to fake reviews. Recently fake review detection has attracted significant attention of both businesses and the acsademicians. For reviews to have genuine user experiences and opinions differentiating between fake and genuine reviews is an imperative thing. Machine learning has been one of the methods used for solving this problem. In this paper, we have collected the reviews from online e-commerce platform primarily dealing in beauty products and used classification algorithms to predict the real and fakeness of reviews and conducted a comparative analysis to study which algorithm classifies the reviews effectively and efficiently on the basis of Accuracy, Precision, F-Measure and Recall.

View PDFchevron_right
Fake Reviews Detection using Supervised Machine Learning
Ahmed Elmogy

International Journal of Advanced Computer Science and Applications

With the continuous evolve of E-commerce systems, online reviews are mainly considered as a crucial factor for building and maintaining a good reputation. Moreover, they have an effective role in the decision making process for end users. Usually, a positive review for a target object attracts more customers and lead to high increase in sales. Nowadays, deceptive or fake reviews are deliberately written to build virtual reputation and attracting potential customers. Thus, identifying fake reviews is a vivid and ongoing research area. Identifying fake reviews depends not only on the key features of the reviews but also on the behaviors of the reviewers. This paper proposes a machine learning approach to identify fake reviews. In addition to the features extraction process of the reviews, this paper applies several features engineering to extract various behaviors of the reviewers. The paper compares the performance of several experiments done on a real Yelp dataset of restaurants reviews with and without features extracted from users behaviors. In both cases, we compare the performance of several classifiers; KNN, Naive Bayes (NB), SVM, Logistic Regression and Random forest. Also, different language models of n-gram in particular bi-gram and tri-gram are taken into considerations during the evaluations. The results reveal that KNN(K=7) outperforms the rest of classifiers in terms of f-score achieving best f-score 82.40%. The results show that the f-score has increased by 3.80% when taking the extracted reviewers behavioral features into consideration.

View PDFchevron_right
Automated Spam Review Detection Using Hybrid Deep Learning on Arabic Opinions
Khaled M . Alalayah

Computer Systems Science and Engineering

Online reviews regarding purchasing services or products offered are the main source of users' opinions. To gain fame or profit, generally, spam reviews are written to demote or promote certain targeted products or services. This practice is called review spamming. During the last few years, various techniques have been recommended to solve the problem of spam reviews. Previous spam detection study focuses on English reviews, with a lesser interest in other languages. Spam review detection in Arabic online sources is an innovative topic despite the vast amount of data produced. Thus, this study develops an Automated Spam Review Detection using optimal Stacked Gated Recurrent Unit (SRD-OSGRU) on Arabic Opinion Text. The presented SRD-OSGRU model mainly intends to classify Arabic reviews into two classes: spam and truthful. Initially, the presented SRD-OSGRU model follows different levels of data preprocessing to convert the actual review data into a compatible format. Next, unigram and bigram feature extractors are utilized. The SGRU model is employed in this study to identify and classify Arabic spam reviews. Since the trial-and-error adjustment of hyperparameters is a tedious process, a white shark optimizer (WSO) is utilized, boosting the detection efficiency of the SGRU model. The experimental validation of the SRD-OSGRU model is assessed under two datasets, namely DOSC dataset. An extensive comparison study pointed out the enhanced performance of the SRD-OSGRU model over other recent approaches.

View PDFchevron_right

References (86)

  1. Anderson M, Magruder J. Learning from the crowd: regression discontinuity estimates of the effects of an online review database. Econ J. 2012;122(563):957-89.
  2. Luca M. Reviews, reputation, and revenue: the case of yelp. com. In: Com (March 15, 2016). Harvard Business School NOM Unit Working Paper,2016; no. 12-016.
  3. Park C-H, Kim Y-G. Identifying key factors affecting consumer purchase behavior in an online shopping context. Int J Retail Dis- trib Manage. 2003.
  4. Jindal N, Liu B. Opinion spam and analysis. In: Proceedings of the 2008 international conference on web search and data mining, 2008; pp. 219-30.
  5. Wu Y, Ngai EW, Wu P, Wu C. Fake online reviews: literature review, synthesis, and directions for future research. Decis Sup- port Syst. 2020;132: 113280.
  6. Li A, Qin Z, Liu R, Yang, Y, Li D. Spam review detection with graph convolutional networks. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Manage- ment, 2019; pp. 2703-11.
  7. Lau RY, Liao S, Kwok RC-W, Xu K, Xia Y, Li Y. Text mining and probabilistic language modeling for online review spam detection. ACM Trans Manage Inf Syst (TMIS). 2012;2(4):1-30.
  8. Ott M, Cardie C, Hancock J. Estimating the prevalence of decep- tion in online review communities. In: Proceedings of the 21st international conference on World Wide Web, 2012; pp. 201-10.
  9. López V, Del Río S, Benítez JM, Herrera F. Cost-sensitive lin- guistic fuzzy rule based classification systems under the mapre- duce framework for imbalanced big data. Fuzzy Sets Syst. 2015;258:5-38.
  10. Fei G, Mukherjee A, Liu B, Hsu M, Castellanos M, Ghosh R. Exploiting burstiness in reviews for review spammer detection. In: Proceedings of the International AAAI Conference on Web and Social Media, 2013; vol. 7, no. 1.
  11. Mukherjee A, Liu B, Glance N. Spotting fake reviewer groups in consumer reviews. In: Proceedings of the 21st international conference on World Wide Web, 2012; pp. 191-200.
  12. Wang C-C, Day M-Y, Chen C-C, Liou J-W. Detecting spamming reviews using long short-term memory recurrent neural network framework. In: Proceedings of the 2nd International Conference on E-commerce, E-Business and E-Government, 2018; pp. 16-20.
  13. Weng H, Ji S, Duan F, Li Z, Chen J, He Q, Wang T. Cats: cross- platform e-commerce fraud detection. In: 2019 IEEE 35th Inter- national Conference on Data Engineering (ICDE). IEEE, 2019; pp. 1874-85.
  14. Rayana S, Akoglu L. Collective opinion spam detection: bridging review networks and metadata. In: Proceedings of the 21th acm sigkdd international conference on knowledge discovery and data mining, 2015; pp. 985-94.
  15. Shehnepoor S, Salehi M, Farahbakhsh R, Crespi N. Nets- pam: a network-based spam detection framework for reviews in online social media. IEEE Trans Inf Forensics Secur. 2017;12(7):1585-95.
  16. Wang X, Liu K, Zhao J. Handling cold-start problem in review spam detection by jointly embedding texts and behaviors. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2017; pp. 366-76.
  17. Ren Y, Ji D. Learning to detect deceptive opinion spam: a sur- vey. IEEE Access. 2019;7:42934-45.
  18. Vidanagama DU, Silva TP, Karunananda AS. Decep- tive consumer review detection: a survey. Artif Intell Rev. 2020;53(2):1323-52.
  19. Lai C, Xu K, Lau RY, Li Y, Jing L. Toward a language modeling approach for consumer review spam detection. In: 2010 IEEE 7th International Conference on E-Business Engineering. IEEE, 2010; pp. 1-8.
  20. Viviani M, Pasi G. Quantifier guided aggregation for the veracity assessment of online reviews. Int J Intell Syst. 2017;32(5):481-501.
  21. Fontanarava J, Pasi G, Viviani M. An ensemble method for the credibility assessment of user-generated content. In: Proceedings of the International Conference on Web Intelligence, 2017; pp. 863-8.
  22. Noekhah S, Fouladfar E, Salim N, Ghorashi SH, Hozhabri AA. A novel approach for opinion spam detection in e-commerce. In: Proceedings of the 8th IEEE international conference on E-com- merce with focus on E-trust, 2014.
  23. Yang X. One methodology for spam review detection based on review coherence metrics. In: Proceedings of 2015 International Conference on Intelligent Computing and Internet of Things. IEEE, 2015; pp. 99-102.
  24. Li H, Liu B, Mukherjee A, Shao J. Spotting fake reviews using positive-unlabeled learning. Computación y Sistemas. 2014;18(3):467-75.
  25. You Z, Qian T, Liu B. An attribute enhanced domain adaptive model for cold-start spam review detection. In: Proceedings of the 27th International Conference on Computational Linguistics, 2018; pp. 1884-95.
  26. Li Q, Wu Q, Zhu C, Zhang J, Zhao W. An inferable representation learning for fraud review detection with cold-start problem. In: 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 2019; pp. 1-8.
  27. Xie S, Wang G, Lin S, and Yu PS. Review spam detection via temporal pattern discovery. In: Proceedings of the 18th ACM SIG- KDD international conference on Knowledge discovery and data mining, 2012, pp. 823-31.
  28. Wang G, Xie S, Liu B, Philip SY. Review graph based online store review spammer detection. In: IEEE 11th international conference on data mining. IEEE. 2011;2011:1242-7.
  29. Wang G, Xie S, Liu B, Yu PS. Identify online store review spam- mers via social review graph. ACM Trans Intell Syst Technol (TIST). 2012;3(4):1-21.
  30. Hussain N, Mirza HT, Hussain I, Iqbal F, Memon I. Spam review detection using the linguistic and spammer behavioral methods. IEEE Access. 2020;8:53801-16.
  31. Aghakhani H, Machiry A, Nilizadeh S, Kruegel C, Vigna G. Detecting deceptive reviews using generative adversarial net- works. In: IEEE Security and Privacy Workshops (SPW). IEEE. 2018;2018:89-95.
  32. Zheng P, Yuan S, Wu X, Li J, and Lu A. One-class adversarial nets for fraud detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, 2019, pp. 1286-93.
  33. Chen C. Mining the web: discovering knowledge from hypertext data. J Am Soc Inf Sci. 2004;55(3):275.
  34. Mukherjee A, Venkataraman V, Liu B, Glance N, et al. Fake review detection: classification and analysis of real and pseudo reviews. UIC-CS-03-2013. Technical Report, 2013.
  35. Alom Z, Carminati B, and Ferrari E. Detecting spam accounts on twitter. In: 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM). IEEE, 2018, pp. 1191-8.
  36. Swe MM and Myo NN. Fake accounts detection on twitter using blacklist. In: 2018 IEEE/ACIS 17th International Conference on Computer and Information Science (ICIS). IEEE, 2018, pp. 562-6.
  37. Jia S, Zhang X, Wang X, and Liu Y. Fake reviews detection based on lda. In: 2018 4th International Conference on Informa- tion Management (ICIM). IEEE, 2018, pp. 280-3.
  38. Aritsugi M, et al. Exploiting function words feature in clas- sifying deceptive and truthful reviews. In: 2018 Thirteenth International Conference on Digital Information Management (ICDIM). IEEE, 2018, pp. 51-6.
  39. Mesnil G, Mikolov T, Ranzato M, and Bengio Y. Ensemble of generative and discriminative techniques for sentiment analysis of movie reviews. arXiv preprint; 2014. arXiv: 1412. 5335.
  40. Yang X and Yu X. Recognizing deceptive reviews based on weighted multi-instance unbalanced support vector machine. In: Proceedings of the 2019 International Conference on Artificial Intelligence and Computer Science, 2019, pp. 705-8.
  41. Kennedy S, Walsh N, Sloka K, Mccarren A, and Foster J. Fact or factitious? Contextualized opinion spam detection. In: Pro- ceedings of the 57th Annual Meeting of the association for com- putational linguistics: student research workshop, 2019.
  42. Devlin J, Chang MW, Lee K, and Toutanova K. Bert: pre-train- ing of deep bidirectional transformers for language understand- ing. 2018.
  43. Nilizadeh S, Aghakhani H, Gustafson E, Kruegel C, and Vigna G. Think outside the dataset: Finding fraudulent reviews using cross-dataset analysis. In: The World Wide Web Conference, 2019, pp. 3108-15.
  44. Tingxuan S and Lau RYK. Collective classification for social opinion spam detection. In: Proceedings of the 2019 2nd inter- national conference on data science and information technology, 2019, pp. 181-6.
  45. Sihombing A and Fong ACM. Fake review detection on yelp dataset using classification techniques in machine learning. In: 2019 International conference on contemporary computing and informatics (IC3I). IEEE, 2019, pp. 64-8.
  46. Ott M, Choi Y, Cardie C, and Hancock JT. Finding deceptive opinion spam by any stretch of the imagination. arXiv preprint; 2011. arXiv: 1107. 4557.
  47. Barushka A and Hajek P. The effect of text preprocessing strate- gies on detecting fake consumer reviews. In: Proceedings of the 2019 3rd international conference on e-business and internet, 2019, pp. 13-7.
  48. Hassan R and Islam MR. Detection of fake online reviews using semi-supervised and supervised learning. In: 2019 International conference on electrical, computer and communication engi- neering (ECCE). IEEE, 2019, pp. 1-5.
  49. Prakash P, Shashank N, Arjun M, Yadav PS, Shreyamsa S, and Prazwal N. Fake review prevention using classification and authentication techniques. In: ICT Systems and Sustainability. Springer, 2020, pp. 397-406.
  50. Caruana R and Niculescu-Mizil A. An empirical comparison of supervised learning algorithms. In: Proceedings of the 23rd international conference on machine learning, 2006, pp. 161-8.
  51. Hastie T, Tibshirani R, Friedman J. The elements of statistical learning. 2001. J Roy Stat Soc. 2004;167(1):192-192.
  52. Li H, Chen Z, Liu B, Wei X, Shao J. Spotting fake reviews via collective positive-unlabeled learning. IEEE Int Conf Data Min. 2014;2014:899-904.
  53. Ren Y, Ji D, and Zhang H. Positive unlabeled learning for decep- tive reviews detection. In: Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 2014, pp. 488-98.
  54. Hai Z, Zhao P, Cheng P, Yang P, Li X-L, and Li G. Deceptive review spam detection via exploiting task relatedness and unla- beled data. In: Proceedings of the 2016 conference on empirical methods in natural language processing, 2016, pp. 1817-26.
  55. Wu Z, Cao J, Wang Y, Wang Y, Zhang L, Wu J. hpsd: a hybrid pu-learning-based spammer detection model for product reviews. IEEE Trans Cybernet. 2018;50(4):1595-606.
  56. Yilmaz CM and Durahim AO. Spr2ep: a semi-supervised spam review detection framework. In: 2018 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM). IEEE, 2018, pp. 306-13.
  57. Liu W, Jing W, Li Y. Incorporating feature representa- tion into bilstm for deceptive review detection. Computing. 2020;102(3):701-15.
  58. Barushka A and Hajek P. Review spam detection using word embeddings and deep neural networks. In: IFIP International conference on artificial intelligence applications and innovations. Springer, 2019, pp. 340-50.
  59. Archchitha K and Charles E. Opinion spam detection in online reviews using neural networks. In: 2019 19th International Con- ference on Advances in ICT for Emerging Regions (ICTer), vol. 250. IEEE, 2019, pp. 1-6.
  60. Yuan C, Zhou W, Ma Q, Lv S, Han J, and Hu S. Learning review representations from user and product level information for spam detection. In: 2019 IEEE international conference on data mining (ICDM). IEEE, 2019; pp. 1444-9.
  61. Wang Z, Zhang J, Feng J, Chen Z. Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the AAAI con- ference on artificial intelligence, 2014; vol. 28, no. 1
  62. Nayak A, Chen H, Ruan X, and Ouyang J. Deepspot: understand- ing online opinion spam by text augmentation using sentiment encoder-decoder networks. In: Proceedings of the 3rd ACM SIG- SPATIAL international workshop on analytics for local events and news, 2019, pp. 1-10.
  63. Ren Y, Zhang Y. Deceptive opinion spam detection using neural network. In: Proceedings of COLING 2016, the 26th international conference on computational linguistics: technical papers, 2016; pp. 140-50.
  64. Zhou J, Cui G, Hu S, Zhang Z, Yang C, Liu Z, Wang L, Li C, Sun M. Graph neural networks: a review of methods and applications. AI Open. 2020;1:57-81.
  65. Kindermann R. Markov random fields and their applications. Am Math Soc. 1980.
  66. Sun H, Morales A, Yan X. Synthetic review spamming and defense. In: Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, 2013; pp. 1088-96.
  67. Weng H, Li Z, Ji S, Chu C, Lu H, Du T, He Q. Online e-commerce fraud: a large-scale detection and analysis. In: 2018 IEEE 34th international conference on data engineering (ICDE). IEEE, 2018; pp. 1435-40.
  68. Xue H, Wang Q, Luo B, Seo H, Li F. Content-aware trust propa- gation toward online review spam detection. J Data Inf Quality (JDIQ). 2019;11(3):1-31.
  69. Yuan D, Miao Y, Gong NZ, Yang Z, Li Q, Song D, Wang Q, and Liang X. Detecting fake accounts in online social networks at the time of registrations. In: Proceedings of the 2019 ACM SIGSAC conference on computer and communications security, 2019, pp. 1423-38.
  70. Wang D, Lin J, Cui P, Jia Q, Wang Z, Fang Y, Yu Q, Zhou J, Yang S, and Qi Y. A semi-supervised graph attentive network for financial fraud detection. In: 2019 IEEE international conference on data mining (ICDM). IEEE, 2019, pp. 598-607.
  71. Liu Z, Chen C, Yang X, Zhou J, Li X, and Song L. Heterogene- ous graph neural networks for malicious account detection. In: Proceedings of the 27th ACM international conference on infor- mation and knowledge management, 2018, pp. 2077-85.
  72. Perozzi B, Al-Rfou R, and Skiena S. Deepwalk: online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data min- ing, 2014, pp. 701-10.
  73. Mikolov T, Chen K, Corrado G, and Dean J. Efficient estimation of word representations in vector space. arXiv preprint; 2013. arXiv: 1301. 3781.
  74. Ali Alhosseini S, Bin Tareaf R, Najafi P, and Meinel C. Detect me if you can: Spam bot detection using inductive representation learning. In: Companion proceedings of The 2019 World Wide Web conference, 2019, pp. 148-53.
  75. Hamilton WL, Ying R, and Leskovec J. Inductive representation learning on large graphs. arXiv preprint; 2017. arXiv: 1706. 02216.
  76. Pearl J. Probabilistic reasoning in intelligent systems: networks of plausible inference. Elsevier, 2014.
  77. Wang J, Wen R, Wu C, Huang Y, Xion J. Fdgars: fraudster detec- tion via graph convolutional networks in online app review sys- tem. In: Companion proceedings of The 2019 World Wide Web conference, 2019; pp. 310-6.
  78. Ghadery E, Movahedi S, Faili H, Shakery A. Mncn: a multilingual ngram-based convolutional network for aspect category detection in online reviews. In: Proceedings of the AAAI conference on artificial intelligence, vol. 33, no. 01, 2019; pp. 6441-8.
  79. Dong W, Moses C, Li K. Efficient k-nearest neighbor graph construction for generic similarity measures. In: Proceedings of the 20th international conference on World wide web, 2011; pp. 577-86.
  80. Rakhlin A. "Convolutional neural networks for sentence classifica- tion," GitHub, 2016.
  81. Ott M, Cardie C, Hancock JT. Negative deceptive opinion spam. In: Proceedings of the 2013 conference of the north American chapter of the association for computational linguistics: human language technologies, 2013; pp. 497-501.
  82. He R, McAuley J. Ups and downs: modeling the visual evolution of fashion trends with one-class collaborative filtering. In: Pro- ceedings of the 25th international conference on world wide web, 2016; pp. 507-17.
  83. McAuley J, Targett C, Shi Q, Van Den Hengel A. Image-based recommendations on styles and substitutes. In: Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval, 2015; pp. 43-52.
  84. Jindal N, Liu B. Opinion spam and analysis. In: WSDM'08 -Pro- ceedings of the 2008 international conference on web search and data mining, no. November,2008; pp. 219-29.
  85. Learning to identify review spam. IJCAI international joint con- ference on artificial intelligence, no. January 2011,2011; pp. 2488-93
  86. Mukherjee A, Venkataraman V, Liu B, Glance N. What yelp fake review filter might be doing?. In: Proceedings of the international AAAI conference on web and social media, 2013; vol. 7, no. 1.

Related papers

Spam Review Detection Using Machine Learning
Poonam Dholi

International Journal of Advanced Research in Science, Communication and Technology

With the continuous evolve of E-commerce systems, online reviews are mainly considered as a crucial factor for building and maintaining a good reputation. Moreover, they have an effective role in the decision making process for end users. Usually, a positive review for a target object attracts more customers and lead to high increase in sales. Nowadays, deceptive or fake reviews are deliberately written to build virtual reputation and attracting potential customers. Thus, identifying fake reviews is a vivid and ongoing research area. Identifying fake reviews depends not only on the key features of the reviews but also on the behaviors of the reviewers. This paper proposes a machine learning approach to identify fake reviews. In addition to the features extraction process of the reviews, this paper applies several features engineering to extract various behaviors of the reviewers. The paper compares the performance of several experiments done on a real Yelp dataset of restaurants rev...

View PDFchevron_right
Detection of Deceptive Reviews Using Long Short-Term Memory (LSTM) and Deep Neural Network (DNN
Mahbub Alam

Journal of Technology Innovations and Energy, 2025

Online reviews serve as social proof for potential customers, promoting confidence in businesses. The online marketplace is expanding rapidly on a global scale, with consumers increasingly relying on internet reviews. This influence is especially significant in the digital age, where customers often rely on the opinions of others to guide their purchasing decisions. As these reviews play a crucial role in shaping purchase decisions, some unethical companies are motivated to fabricate and distribute misleading evaluations. Deceptive reviews are fabricated evaluations produced with the intention of appearing real and misleading the consumers. Those deceptive reviews can be detected manually based on their patterns which are seen in their linguistic and psychological aspects. However, the deep learning techniques proposed outperform all conventional approaches and offer higher selfadaptability to extract the desired features implicitly. For the purpose of detecting false reviews, we have suggested a Deep Neural Network (DNN) based Deceptive Review Detection Model (DRDM) method.

View PDFchevron_right
Fake Reviews Detection: A Survey
Rami Mohawesh

IEEE Access, 2021

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. INDEX TERMS Fake review, fake review detection, feature engineering, machine learning, deep learning.

View PDFchevron_right
Survey of review spam detection using machine learning techniques
Hamzah Al-Najada

Online reviews are often the primary factor in a customer's decision to purchase a product or service, and are a valuable source of information that can be used to determine public opinion on these products or services. Because of their impact, manufacturers and retailers are highly concerned with customer feedback and reviews. Reliance on online reviews gives rise to the potential concern that wrongdoers may create false reviews to artificially promote or devalue products and services. This practice is known as Opinion (Review) Spam, where spammers manipulate and poison reviews (i.e., making fake, untruthful, or deceptive reviews) for profit or gain. Since not all online reviews are truthful and trustworthy, it is important to develop techniques for detecting review spam. By extracting meaningful features from the text using Natural Language Processing (NLP), it is possible to conduct review spam detection using various machine learning techniques. Additionally, reviewer information, apart from the text itself, can be used to aid in this process. In this paper, we survey the prominent machine learning techniques that have been proposed to solve the problem of review spam detection and the performance of different approaches for classification and detection of review spam. The majority of current research has focused on supervised learning methods, which require labeled data, a scarcity when it comes to online review spam. Research on methods for Big Data are of interest, since there are millions of online reviews, with many more being generated daily. To date, we have not found any papers that study the effects of Big Data analytics for review spam detection. The primary goal of this paper is to provide a strong and comprehensive comparative study of current research on detecting review spam using various machine learning techniques and to devise methodology for conducting further investigation.

View PDFchevron_right
A Survey Paper on Fake Review Detection System
Nikita Khairnar

New Frontiers in Communication and Intelligent Systems

Nowadays, E-commerce websites has become a vital part of regular life. The pandemic has taken a quick step towards the digital world and initiated changes in online shopping behaviors. While buying products online many people read the reviews related to the product and then decide on buying it. So, reviews play an important role if a customer wants to buy any product. This leads to increased spam review volume in social networks and e-commerce websites like Flipkart, Amazon, etc. Fake reviews can be used to demote a good product or to promote a bad product, so there is a need for robust and reliable techniques to detect fake reviews which can be beneficial to the customer as well as to the vendor. The objective of this survey paper is to get an overview of different methodologies used to solve such problems. This research presents a systematic review on methods to detect spam review using different Deep Learning (DL) Approaches, Machine Learning (ML) Methods, Natural Language Proces...

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved