Privacy-Preserving_Social_Media_Data_Publishing_for_Personalized_Ranking-Based_Recommendation.pptx

Privacy is an mantory for upcoming technology

1. Privacy-Preserving Social Media Data Publishing for Personalized Ranking-Based Recommendation

2. Abstract Personalized recommendation is crucial to help users find pertinent information. It often relies on a large collection of user data, in particular users’ online activity (e.g., tagging/rating/checking-in) on social media, to mine user preference. However, releasing such user activity data makes users vulnerable to inference attacks, as private data (e.g., gender) can often be inferred from the users’ activity data. In this paper, we proposed PrivRank, a customizable and continuous privacy-preserving social media data publishing framework protecting users against inference attacks while enabling personalized ranking-based recommendations.

3. Its key idea is to continuously obfuscate user activity data such that the privacy leakage of user-specified private data is minimized under a given data distortion budget, which bounds the ranking loss incurred from the data obfuscation process in order to preserve the utility of the data for enabling recommendations. An empirical evaluation on both synthetic and real-world datasets shows that our framework can efficiently provide effective and continuous protection of user-specified private data, while still preserving the utility of the obfuscated data for personalized ranking-based recommendation. Compared to state-of-the-art approaches, PrivRank achieves both a better privacy protection and a higher utility in all the ranking-based recommendation use cases we tested.

4. Objective : To Achieve Better Recommendation data set from user feedback in Social media with Privacy Protection over private data Using Collaborative Filtering Algorithum .

5. Existing System In Existing System user activity data as public data. However, they often consider part of the data from their social media profile as private, such as gender, income level, political view, or social contacts. In the following, we refer to those data as private data. Private data often suffers from inference attacks , where an adversary analyzes a user’s public data to illegitimately gain knowledge about her private data. It is thus crucial to protect user private data when releasing public data to recommendation engines.

6. Disadvantage of Existing System Protection on the private data by distorting the public data before its publication, at the expense of a loss of utility of the public data in the latter processing stages. Recommendation engines can not accurately predict the individual’s preference based on the obfuscated data.

7. PROPOSED SYSTEM : Content aware collaborative filtering is propose the integration of content based recommendation and Ranking. To provide effective privacy protection when releasing user data, privacy-preserving data publishing has been widely studied. Its key idea is to obfuscate user data such that published data remains useful for some the predicted ranking list and the actual list from the users. Therefore, different from existing methods that bound data distortion using non-ranking-based measures, our approach considers bounding the ranking loss incurred from the data obfuscation process using personalized ranking-based recommendation.

8. ADVANTAGE Content-aware collaborative filtering is the integration of content-based recommendation and collaborative filtering. Our proposed algorithm targets content-aware collaborative filtering from implicit feedback and successfully addresses the disadvantages by treating the items not preferred by users as negative while assigning them a lower confidence for negative preference and achieving linear time optimization. Accuracy is high.

9. Future Scope : In future, we plan to extend our APR method to other recommender models. First, we are interested in exploring more generic feature-based models like Neural Factorization Machines and Deep Crossing that can support a wide range of recommendation and Ranking based on privacy protection in Social Media.

10. Modules User Credential Post Handling Service Ranking Based web service Comments Reliability

11. User Credential : If the user is a new one then he will hit the ‘new user’ button ,then another frame called ‘login’ will be displayed. If the username and password typed by the user are not matching with the database values, then this frame is called. This frame has only two features namely one is the txt panel displaying the message “USERNAME OR PASSWORD ARE NOT MATHING. PLEASE TRY AGAIN !!!!!!!!!!!!! ”. and On hitting that frame consecutively three times in the sense the concern user accounts will automatically blocked it .

12. PostHandling Service : Here we have given an input post to database using web service insert operation .we can change, delete and update the –post in the table by using service query commands

13. Ranking Based Web Service : In this module after user logged in they can able to rank the post based an their mentality .here we do Collaborative and Bilateral Filtering for post ranking and Recommendation and catching the user’s favorites to optimize the QOS

14. 4.Comments : User can provide positive or negative comments to know post best .based on this service high positive post will be shown to user in the top and negative in the bottom of searching list.

15. 5.Relaiability Reliability is the quality aspect of a Web service that represents the degree of being capable of maintaining the service and service quality. The number of failures per month or year represents a measure of reliability of a Web service.

16. SOFTWARE REQUIREMENTS: Operating system : Windows XP/7. Coding Language : Asp.Net IDE : .Net Framwork4.5 Database : Mssql2008

17. HARDWARE REQUIREMENTS: System : I3 Processer Hard Disk : 500 GB. Monitor : 15 VGA Color. Mouse Ram : 4 GB