A Review on Data Privacy Detection in Social Networks using Data Mining, Machine Learning and Blockchain technologies

Abstract

Data Privacy Detection in Social Networks (DPDSNs) is overriding the need for the privatization of information in online networks and social media. In recent times, data security and privatization have become the biggest challenge for all categories of people ranging from affluent people to familiar people in society. Social networking data being sensitive is capable of causing a big difference in all the domains where sensitive information cases sensations in positive as well as in adverse impacts. The primary objective of this paper is to conduct a deep- rooted review on various aspects of Data Privacy Detection methods applied in Social Networks using combinational analysis of multiple areas like Data Mining, Machine Learning, and Blockchain Technological processes respectively. Numerous papers were surveyed and reviewed with a primary focus on methodologies used, techniques applied, algorithms designed as well as the outcomes of results achieved in the course of the study. After consequent reviews and analysis, a novel framework based on the non-existence of Data Privacy Detection Techniques was proposed, and the future directions are shared to counteract the problems faced in the data privacy along with this study.