Spam Review Detection Using Weighted Swarm Support Vector Machines and Pre-Trained Word Embedding for Multiple Languages
Main Article Content
Abstract
Before making a purchase, many find internet reviews to be a vital source of information. On top of that, companies may learn a lot about their products and services via these reviews. Having faith in these reviews was especially important during the COVID-19 pandemic, when many stayed inside and read reviews at a dizzying pace. The pandemic altered the atmosphere and people's preferences in addition to increasing the number of evaluations. Spam reviewers keep an eye on these changes and try to improve their sneaky techniques. In order to deceive customers or harm competitors, reviews that are deemed spam may include inaccurate, misleading, or dishonest information. Consequently, this work introduces a WSVM plus an HHO to identify spam reviews. The HHO is similar to an algorithm in that it optimises hyperparameters and uses feature weights. Using English, Spanish, and Arabic language corpora as datasets, the multilingual difficulty in spam reviews has been tackled. Ngram-3, TFIDF, whereas One-hot encoding are three methods for representing words, while pre-trained word incorporation (BERT) is another one that has been used. Each of the four such studies has shed light on and provided a solution to a different facet. From start to finish, the proposed technique beat rival cutting-edge algorithms in every test. For the Multi dataset, the WSVM-HHO achieved a success rate of 84.270 percent; for the English information set, 89.565 percent; for the Spanish information set, 71.913 percent; and for the Arabic dataset, 88.565 percent. Furthermore, we have extensively researched the review environment before to and during the COVID-19 event. To further enhance detection performance, it has been designed to merge its existing textual attributes with statistical information to build a new dataset.
Downloads
Metrics
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
References
Int. J. Netw. Securi. Appl. 8 (4) (2016), M. Awad and M. Foqaha classified spam emails by combining RBF neural networks with particle swarm optimisation.
In their 2016 article "Measuring Characterizingand Eliminating Spam Traffic Costs," D.M. Fonseca, O.H. Fazzion, D. Cunha, and I. Las-Casas, Pete Guedes, R. Meira, and M. Chaves discuss methods for assessing and avoiding costly spam traffic.
the third The following website was seen on May 15, 2017, from https://www.securelist.com/en/analysis/204792230/Spam_Report_April_2012: Kaspersky Lab Spam Report, 2017.
the work of E.M. Bahgat, H. Rady, and W. Gad, In: Proceedings of the 1st Worldwide Symposium on Advanced Autonomous System for Informatics (AISI2015), held during November 28-30, 2015, in BeniSuef, Egypt, 2016, pages 321-331, published by Springer International Publishing.
Referenced in [5] Inf. Proc. Manag. 45 (6) (2009) 631-642, Bouguila and Amayri provide a discrete mixture-based core for support vector machines (SVMs) with applications in spam and image classification.
In: the International Conference on Neural Networks, Elsevier Berlin Heidelberg in Germany, 2004, pp. 688-694, Y. Cao, X. Liao, and Y. Li present an e-mail filtering strategy using neural networks.
SpamHunting: an instance-based logic framework for spam tagging and filtering, by F. Fdez-Riverola, She Iglesias, F. Diaz, who was J.R. Mendez, also and J.M. Corchado, [7] Volume 43, Issue 3, July 2007, pages 722–736, Decision Support Systems.
S. Mason, A New Law to Reduce Email Spam, 2003. Here is the link: http://www.wral.com/technolog.
Stuart, I., Cha, S.H., and Tappert, C. [9] Volume VI of Document Analysis Systems, Springer Berlin Heidelberg, 2005, pages 442-450, presents a neural network classifier for spam email.
Data Mining: Fundamentals and Strategies, J. Han, H. Kamber, and J. Pei, Published by Elsevier in 2011.
The authors of the article "Multi-objective hybrid algorithms towards neural network with radial basis functions design" (27, 475–497) are S.N. Qasem, S.M. Shamsuddin, and A.M. Zain.
In Combinations of Genetic Methods with Neural Networks, published in 1992, pp. 1-37, J.D. Schaffer, who was, D. Whitley, who was and L. Eshelman surveyed the current state of the art in the field.
In Adv. Comp. Inf. 19 (2004) 43–53, Elbeltagi, Hegazy, and Grierson compare five optimisation techniques based on evolution.
The workload models of spammers and valid e-mails were developed by L.H. Gomes, the process C. Cazita, and J.M. In the words of Al V. In the case of Al and W.J. Meira [14]. Eval. Perform. 64 (7-8) 690-714 (2007).
Citation: [15] C.C. Wang, the S.Y. Chen, Computer Security 26(5):381-390 (2007) discusses the use of header session messages for anti-spam purposes.
P.S. Guzella and W.M. Caminhas [16] Expert Systems, Applications, and Machine Learning, 36(7), 10206–10222 (2009).
In Proc. Assoc. Inf. Eng. Technol. 42 (1) (2005), C.P. Lueg discusses the transition from blocking spam to info retrieval and back: finding conceptual underpinnings for spam filtering.
In the 2005 International Seminar on Automated Learning and Cybernetics (Volume 9, pp. 5716-5719), published by IEEE in August 2005, X.L. Wang surveyed the state of learning to categorise emails.
In: Paper presented at the European Seminar on Web Intelligent Meets Brain Informatics, 2006, W. Li, N. Zhong, H. Yao, J. Liu, and C. Liu discuss filters for spam and email-mediated applications.
Email spam filtering: an exploratory study, Ent. Developments Inform. Retr. 1 (4) (2008), further 335-455, G.V. Cormack, 2008, p. 335.
In Adv. Computer Science 74 (2008) 45-114, E.P. He, J.M.G. Hidalgo, and J.C.C. Perez discuss email spam filtering.
B. Karthikeyani, S. Dhanaraj, Research on methods for detecting spam images transmitted by email, in: 2013 International Forum on Pattern Recognition, Informatics, and Mobile Engineering (PRIME) paper.
The Machine Learning Strategies for E- Email Email Passing: Check it out Techniques and Trends, by A. Bhowmick and S.M. Hazarika, arXiv:1606.01042v1. The line [cs.LG] June 3, 2016, pages 1–27.
The efficacy of anomaly recognition for spam filtering was investigated in a study by C. Laorden, A. Ugarte-Pedrero, D. Santos, D. Sanz, J. Nieves, and P.G. Bringas (2015) in Inf. Sci. 277, 421-444.
The A. Vakali and G. Pallis (Eds.), Web Database Management Practices: Emerging Strategies and Technologies, Concept Group Publishing, USA, 2007, chap. 10, discusses email mining as one of the emerging strategies for email management.