Detection of Deceptive Hotel Reviews Through the Application of Machine Learning Techniques

In the contemporary digital landscape, online reviews play a pivotal role in shaping tourists’ decisions, leveraging the pervasive influence of the internet. However, discerning the authenticity of reviews has become an intricate challenge, blurring the line between genuine and deceptive evaluations. This ambiguity provides fertile ground for individuals seeking to exploit the uncertainty, as witnessed in the proliferation of false reviews and the spread of unfavorable rumors through social media platforms. The consequences are profound, with travelers and hosts alike navigating a landscape where traditional verification systems prove insufficient, leaving consumers vulnerable to misinformation. To address this pressing issue, we propose a novel machine learning-based approach. Our strategy employs classifiers such as Random Forest, Support Vector Machine, and Decision Tree, each exhibiting robust validation accuracy values of 92.19%, 87.19%, and 86.56%, respectively. This innovative framework serves as a powerful tool to distinguish between authentic and fraudulent reviews, providing a more reliable foundation for decision-making in the travel sector. By leveraging the capabilities of machine learning, we aim to create a system that not only identifies deceptive practices but also contributes to restoring trust in online reviews. As the travel industry contends with the challenges posed by the digital era, this approach offers a promising avenue for mitigating the impact of false information and enhancing the overall integrity of the review ecosystem.