USER - UPLOADED IMAGES PRIVACY POLICY PREDICTION USING CLASSIFICATION AND POLICY MINING

Social media become one of the most essential part of our daily life as it enables us to be in touch with a lot of people. Creation of social networking sites such as LinkedIn, Facebook and MySpace give opportunities to communicate new peoples and friends in their own and also in the other various communities across the world. Users of social media share plenty of personal information with a large number of “friends.” These enhance technology leads to violations of privacy as the users are sharing the large volumes of images across more number of people. This privacy need to be concerned in order to improve the user satisfaction level. Toward addressing this need, an Adaptive Privacy Policy Pr ediction (A3P) system is provided to help users compose privacy settings for their images. The role of social context, image content, and metadata examine as possible indicator of user’s privacy preferences. According to the user’s available history on the social site, A3P system determines the best existing privacy policy for the user’s images being uploaded. The result relies on an image classification structure for image categories which may be related to the same type of policies, and on a policy predic tion algorithm for automatically generate a policy for each newly uploaded image, also according to the social features of the user. Our overarching goal is to provide better tools for managing privacy of information shared in the social media sites.