In today's digital era, social media content, such as reviews and comments, plays a significant role in shaping people's opinions. However, this widespread availability of user-generated content also creates opportunities for spammers to post spam reviews for various purposes. While several studies have focused on identifying and detecting spam content, existing approaches often fail to capture the significance of each extracted feature type and struggle to detect spam reviews effectively.
This project introduces a novel framework called NetSpam, which leverages spam features to characterize review datasets as heterogeneous information networks. By mapping spam detection into a classification problem within these networks, NetSpam improves the performance metrics on actual review datasets from popular websites like Yelp and Amazon. The results demonstrate that NetSpam outperforms existing approaches, with the review-behavioral feature type surpassing the others among the four types (review-behavioral, user-behavioral, review-linguistic, and user-linguistic).
The Netspam detection final year project is based on an IEEE Paper and is considered one of the best projects for computer science students. As the best IEEE project maker in Bangalore, we provide complete documentation support, fully implemented hardware/software in the students' environment, and structured classes to ensure a successful project development process.