Spam Detection Framework for Reviews in Online Social Sites
The impact of social spam is already significant. A social spam message is potentially seen by all the followers and recipients’ friends. Even worse, it might cause misdirection and misunderstanding in public and trending topic discussions. Amazon websites is the most commonly used datasets of experimental data. The results show that Net Spam outperforms the existing methods and among four categories of features; including review-behavioral, user-behavioral, review-linguistic, user-linguistic. The possibility that anyone can leave a review offers a spam on spam reviews about products and services. Spam Detection for Social Sites Reviews Identifying these spammers and spam content is a very important issue. For that we introduce a novel algorithm content based filtering to filtering the normal review and spam based review. Features for the detection of spammers could be user based or content based or both and spam classifier methods.
Spam Detection for Social Sites Reviews
Existing System
The results show that NetSpam outperforms the existing methods and among four categories of features; including review-behavioral, use behavioral, review linguistic, user linguistic, the first type of features performs better than the other categories.
Despite this great deal of efforts, many aspects have been missed or remained unsolved. One of them is a classifier that can calculate feature weights that show each feature’s level of importance in determining spam reviews. The general concept of our proposed framework is to model a given review dataset as a Heterogeneous Information Network (HIN) and to map the problem of spam detection into a HIN classification problem. In particular, we model review dataset as a HIN in which reviews are connected through different node types. The general concept of our proposed framework is to model a given review dataset as a Heterogeneous Information Network and to map the problem of spam detection into a HIN classification problem. In particular, we model review dataset as in which reviews are connected through different node types.
DISADVANTAGES
- The reviews written to change users’ perception of how good a product or a service are considered as spam , and are often written in exchange for money
- Time Complexity.
- The fact that anyone with any identity can leave comments as review, provides a tempting opportunity for spammers to write fake reviews designed to mislead users’ opinion
Proposed System
In this paper, they have introduced a machine learning based spammer detection solution for social networks. The solution considers the user’s content and behavior feature, and apply them into Content based Filtering algorithm for spammer classification. Through a multitude of analysis, experiment, evaluation and prototype implementation work, have shown that proposed solution is feasible and is capable to reach much better classification result than the other existing approaches. A spam detection prototype system has been proposed to identify suspicious users in Online shopping websites. The social-spam detection framework can be split into two main components. First one OTP System. In this system user enter their reviews only after purchasing the product by using this code. This OTP system we can used in two process one is for enter review login and another one for viewing the both positive and negative feature based review.Second components to discover fake review users by using content based filtering algorithm. These functions are designed to help server side (seller side) to discover spammer easily and blocked spam users. To detect the frequent spammers by using credit based approach.
ADVANTAGES:
- To identify spam and spammers as well as different type of analysis on this topic.
- Written reviews also help service providers to enhance the quality of their products and services
- By using features with more weights will resulted in detecting fake reviews easier with less time complexity
- To Introduce credit point ranking system by using this we can able to find out the frequent spammers
- To introduce one time password system to prevent the fake reviews.
HARDWARE REQUIREMENTS
System : Intel3core
HardDisk : 8GB
Monitor : 14’ColorMonitor
Mouse : Optical Mouse
SOFTWARE REQUIREMENTS
Operating system : Windows7/8/10
Coding Language : ASP.Net with C# (Service Pack 1)
Data Base : SQL Server 2014
Tools : Visual studio 2013
Modules
- USER
- SELLER
- ADMIN
User:
- Login
- View All Products
- View Top Ranking Product
- Insert Review For Particular Product
- Logout
Admin:
- View All Users
- Activate Account
- View Top Product
- View Recommend Product
- View All Review Details
Seller
- Update Product
- View Product Details
