Deceptive web-review detection strategies: a survey. (5th February 2023)

• Record Type: Journal Article
• Authors: Boparai, Rajdavinder Singh; Bhatia, Rekha
• Is Part Of: International journal of intelligent engineering informatics. Volume 10:Number 5(2022)
• Page Start: 411
• Page End: 433
• Publication Date: 2023-02-05
• Subjects: deceptive -- review -- machine learning -- lexicon -- web review -- survey -- classifier; Artificial intelligence -- Engineering applications -- Periodicals; Engineering -- Computer programs -- Periodicals; Knowledge management -- Periodicals; 620.0028563
• Languages: English
• ISSNs: 1758-8715

Abstract

Deceptive reviews on internet platforms are a harsh reality in today's world. Specific services, businesses, and products are praised or vilified in these reviews. In an online or web society, users get help from reviews before making a decision, and in a similar way, web reviews are also very helpful for organisations to keep them updated as per customer needs. A lot of effort has gone into detecting this sort of review. Apart from evaluating state-of-the-art research papers on fraudulent review identification, a taxonomy of machine learning algorithms for detecting deceptive or non-genuine web reviews is provided in this paper. It begins with a broad introduction to sentiment analysis, web reviews, deceptive reviews, and machine learning. Thereafter, providing crucial information regarding available deceptive review detection approaches, along with datasets, methodologies, and their performance. It critically summarises existing techniques to find out research gaps w.r.t. supervised, unsupervised, and semi-supervised methods and also quantitatively with the help of specific datasets such as Yelp and AWS. The paper also looks at research gaps and future recommendations for detecting deceptive reviews.