Informed Choices: Identifying Deceptive in Online Reviews

Nowadays, there is a lack of genuine reviews in various domains, such as business, politics, and media. In order to safeguard the integrity of information and decision-making processes, this project develops an effective system for identifying and mitigating deceptive analysis in different fields especially in an era where misinformation and manipulation are becoming more prevalent. The development of deceptive analysis utilizing machine learning is an essential solution in the ever-changing landscape of online reviews. The proposed system is an online application accessible both within the organization and externally, ensuring secure access with proper authentication mechanisms. In the digital age, online reviews wield considerable influence in the global marketplace. Consumers depend on these reviews to make well-informed choices regarding products and services. To address this challenge, this project employs two powerful machine learning techniques: Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Classification and Regression Trees (CART). These methodologies provide a multifaceted approach to detect deceptive content within online reviews. The used algorithms give genuine reviews and results in an accuracy of 88.83%.