Modeling Language Vagueness in Privacy Policies using Deep Neural Networks

Abstract: Website privacy policies are too long to read and difficult to understand. The over-sophisticated language makes privacy notices to be less effective than they should be. People become even less willing to share their personal information when they perceive the privacy policy as vague. This paper focuses on decoding vagueness from a natural language processing perspective. While thoroughly identifying the vague terms and their linguistic scope remains an elusive challenge, in this work we seek to learn vector representations of words in privacy policies using deep neural networks. The vector representations are fed to an interactive visualization tool (LSTMVis) to test on their ability to discover syntactically and semantically related vague terms. The approach holds promise for modeling and understanding language vagueness.