Predicting and Analyzing Privacy Settings and Categories for Posts on Social Media

While social media is prevalent in people's daily life, privacy control of user-generated posts is becoming increasingly important. In this paper, we propose to enable automatic privacy control for social media posts through two tasks, predicting privacy settings and predicting privacy categories. The former is to recommend the proper settings of privacy levels, including family, close, casual, and outside, for a post. The latter is to predict the categories of privacy concerns for a post. We propose a multi-task learning-based approach, along with learning feature representation of each post, for such two tasks. Experiments conducted on a real dataset with tweet posts exhibit promising performance of our model, and thus encourage further investigation of privacy-related tasks for privacy control on social media. We also provide a series of extensive analysis with insights that reveal the hidden correlation between privacy settings/categories and post texts.