PRIVACY PRESERVING SOCIAL MEDIA DATA PUBLISHING FOR PERSONALIZE RANKING-BASED RECOMMENDATION
DOI:
https://doi.org/10.62643/Keywords:
Privacy Preservation, Social Media, Recommendation System, Data Anonymization, Differential Privacy, Ranking Algorithms, Machine Learning, Data Security.Abstract
ve data raises significant privacy concerns, as unauthorized access or data leakage can compromise user confidentiality. This project focuses on developing a privacy-preserving framework for publishing social media data while enabling effective personalized ranking-based recommendations. The proposed system employs data anonymization and privacypreserving techniques such as k-anonymity, differential privacy, and data perturbation to protect sensitive user information before publishing. At the same time, it ensures that the utility of the data is maintained for recommendation purposes. A ranking-based recommendation model is applied to analyze user preferences and generate personalized content recommendations. Machine learning algorithms are used to learn user behavior patterns and rank items based on relevance, improving user experience without compromising privacy. The system includes modules for data preprocessing, privacy preservation, model training, and recommendation generation. Experimental results show that the proposed approach successfully balances privacy protection and recommendation accuracy. While strong privacy mechanisms may slightly affect data utility, the system achieves an optimal tradeoff between privacy and performance. This project highlights the importance of integrating privacy-preserving techniques into recommendation systems and provides a scalable solution for secure social media data sharing.
Downloads
Published
Issue
Section
License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.













