Research Article
A Privacy Settings Prediction Model for Textual Posts on Social Networks
@INPROCEEDINGS{10.1007/978-3-030-00916-8_53, author={Lijun Chen and Ming Xu and Xue Yang and Ning Zheng and Yiming Wu and Jian Xu and Tong Qiao and Hongbin Liu}, title={A Privacy Settings Prediction Model for Textual Posts on Social Networks}, proceedings={Collaborative Computing: Networking, Applications and Worksharing. 13th International Conference, CollaborateCom 2017, Edinburgh, UK, December 11--13, 2017, Proceedings}, proceedings_a={COLLABORATECOM}, year={2018}, month={10}, keywords={Social networks Privacy Policy recommendation}, doi={10.1007/978-3-030-00916-8_53} }- Lijun Chen
Ming Xu
Xue Yang
Ning Zheng
Yiming Wu
Jian Xu
Tong Qiao
Hongbin Liu
Year: 2018
A Privacy Settings Prediction Model for Textual Posts on Social Networks
COLLABORATECOM
Springer
DOI: 10.1007/978-3-030-00916-8_53
Abstract
Privacy issues of social media are getting tricky due to the increasing volume of social media users sharing through online social networks (OSNs). Existing privacy policy mechanisms of OSNs may not protect personal privacy effectively since users are struggle to set up the privacy settings. In this paper, we propose a privacy policy prediction model to help users to specify privacy policies for their textual posts. We investigate the semantic of posts, social context, and keywords associated with users’ privacy preferences as possible indicators of decision making, and build a multi-class classifier based on their historical posts and decisions. During the cold-start periods, the proposed model integrates crowdsourcing and machine learning to recommend privacy policies for new users. Experimental results shows that the overall match rate for all the data with random forest classifier is over 70%, with more than 50% correct prediction rate for new users.