Abstract

In recent years, online reviews have become a crucial factor in promoting products and services. However, the rise of fake reviews has posed a significant challenge. Businesses, marketers, and advertisers often resort to embedding fake reviews to attract customers or undermine their competitors. Deceptive reviews have become a common practice, as they serve as a means of promoting one''''s own business or tarnishing the reputation of rivals. Consequently, the identification of deceptive reviews has emerged as a critical and ongoing research area. This research paper presents a machine learning model approach to detect deceptive reviews. The study focuses on experiments conducted using a deceptive opinion spam corpus dataset, specifically targeting restaurant reviews. An n-gram model combined with max features is developed to identify deceptive content, with a particular emphasis on fake reviews. Additionally, a benchmark study is conducted to explore the performance of two different feature extraction techniques and their application in five machine learning classification techniques. The experimental findings demonstrate that the passive aggressive classifier outperforms other algorithms, achieving the highest accuracy not only in text classification but also in identifying fake reviews. Moreover, the research delves into the identification of deceptive reviews and explores diverse feature extraction and machine learning techniques to improve the model''''s accuracy.