A Multifaceted Novel Approach to Identify Deceptive Reviews Based on Psychology Theories: A New Dataset

Authors

  • Abeer Hassan Asiri Faculty of Computer and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia
  • Fahad Mazaed Alotaibi Faculty of Computer and Information Technology, King Abdulaziz University, Jeddah, Saudi Arabia

Abstract

As deception negatively impacts various areas, deception detection is an important field of study. This paper introduces a framework to detect online review deception. It studied aspects of deceptive reviews, considering the complex nature of deception in textual data and the low chance of direct detection. Furthermore, the paper presents a new corpus for deceptive reviews labeled using deception hints. This dataset was compiled in English and extracted from Google Maps reviews. We focused on the reviews of “restaurants” in New York. The novelty of this dataset is that the truthful and deceptive reviews were not deliberately collected; that is, participants were not requested to write lies, but the texts were collected after the individuals had written them. We used predefined criteria using deception indicators to differentiate deceptive and truthful reviews for this dataset. Each suggested indicator is not a definitive indicator on its own, but we assessed review authenticity using a set of indicators together. This paper aims to discuss lie detection strategies and theories, design a theory-based framework to detect deception in online reviews and implement the framework on a real-world dataset to provide a foundation for future empirical research and practical applications. The experimental results obtained from our labeled benchmark dataset showcase the effectiveness of this approach.

Downloads

Download data is not yet available.

Published

30-07-2025

How to Cite

Asiri, A. H., & Alotaibi, F. M. (2025). A Multifaceted Novel Approach to Identify Deceptive Reviews Based on Psychology Theories: A New Dataset. Communications in Mathematics and Applications, 16(1), 375–404. Retrieved from https://www.journals.rgnpublications.com/index.php/cma/article/view/3310

Issue

Vol. 16 No. 1 (2025)

Section

Review Article

License

Creative Commons Licence 4.0 by  

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a CCAL that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.