Detecting and editing privacy policy pitfalls on the web

Privacy policies are the locus where consequences concerning privacy and personal data are produced, but content features explain why they are largely ignored by its addressees. To abridge users with policies, we propose a policybased system that identifies potential pitfalls in the privacy policies of companies on the Web. It will then suggest clarification of terms by suggesting removal or replacement of defective terms, in order to foster accountable policymaking and compliance. The proposed methods are based on extracting knowledge from natural language texts of a small sample size, and on semantic representations of the policy expression.