In today's world, a significant portion of people base their judgments on the social media content that is readily available (such as reviews and comments on a subject or product). Anyone having the ability to post a review presents a fantastic opportunity for spammers to write spam reviews on goods and services for various purposes.
Although many studies have been conducted recently with the goal of identifying these spammers and their spam content, none of them demonstrate the significance of each extracted feature type, and the approaches now in use hardly ever discover spam reviews. In this project, we offer a novel framework called NetSpam that uses spam features to characterise review datasets as heterogeneous information networks to map a method of spam detection into a classification issue in such networks. We can improve the outcomes of several metrics tested on actual review datasets from the Yelp and Amazon websites by utilising the significance of spam features. The results demonstrate that NetSpam performs better than the current approaches, and among the four types of features (review-behavioral, user-behavioral, reviewlinguistic, and user-linguistic), the first type surpasses the others.
Netspam detection final year project is based on IEEE Paper.this will be one of the best Final year engineering project for computer science.
Components that we will provide are.
1.complete documentation support
2.complete working hardware/software implemented in students environment
3.classes will held accordingly.