Social networks provide convenience for users but pose some risks at the same time. While publishing information online, users can accidentally disclose personal information, such as email address, hometown, or activities attended. A tool which would automatically detect personal information and reminding user would be hence useful.
Recently, a group of researchers proposed an extended version of their older privacy leakage detection framework. It combines both deep learning and ontology models. The deep learning model detects the privacy leakage on online social data.
The ontology privacy model is developed from massive data collected from real-world social networks and classifies the information into nine subtypes. Therefore, not only users are reminded that they are going to post sensitive information but also notified what the kind of private data is concerned. It may help the user to avoid repeating the mistake again.
A large amount of information has been published to online social networks every day. Individual privacy-related information is also possibly disclosed unconsciously by the end-users. Identifying privacy-related data and protecting the online social network users from privacy leakage turn out to be significant. Under such a motivation, this study aims to propose and develop a hybrid privacy classification approach to detect and classify privacy information from OSNs. The proposed hybrid approach employs both deep learning models and ontology-based models for privacy-related information extraction. Extensive experiments are conducted to validate the proposed hybrid approach, and the empirical results demonstrate its superiority in assisting online social network users against privacy leakage.
Research paper: Wu J., Li W., Bai Q., Ito T., Moustafa A., Privacy Information Classification: A Hybrid Approach. 2021, arXiv, arXiv:2101.11574. Link: https://arxiv.org/abs/2101.11574