Journal Article

Improving Readability of Online Privacy Policies through DOOP: A Domain Ontology for Online Privacy

Audich, Dhiren A., Nonnecke, Blair, Dara, Rozita

2021

Overview

Privacy policies play an important part in informing users about their privacy concerns by operating as memorandums of understanding (MOUs) between them and online services providers. Research suggests that these policies are infrequently read because they are often lengthy, written in jargon, and incomplete, making them difficult for most users to understand. Users are more likely to read short excerpts of privacy policies if they pertain directly to their concern. In this paper, a novel approach and a proof-of-concept tool are proposed that reduces the amount of privacy policy text a user has to read. It does so using a domain ontology and natural language processing (NLP) to identify key areas of the policies that users should read to address their concerns and take appropriate action. Using the ontology to locate key parts of privacy policies, average reading times were substantially reduced from 29–32 min to 45 s.

• Publisher: MDPI AG
• Subject: Automation / Computer privacy / Crowdsourcing / Legal documents / Machine learning / Natural language processing / Ontology / Personal information / Privacy / Readability / Reading / Semantics / Subject specialists