Systematic machine translation of social network data privacy policies

• Main Authors: Tanoli, Irfan Khan, Amin, Imran, Junejo, Faraz, Yusoff, Nukman
• Format: Article
• Published: MDPI 2022
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://eprints.um.edu.my/40871/

With the growing popularity of online social networks, one common desire of people is to use of social networking services for establishing social relations with others. The boom of social networking has transformed common users into content (data) contributors. People highly rely on social sites to share their ideas and interests and express opinions. Social network sites store all such activities in a data form and exploit the data for various purposes, e.g., marketing, advertisements, product delivery, product research, and even sentiment analysis, etc. Privacy policies primarily defined in Natural Language (NL) specify storage, usage, and sharing of the user's data and describe authorization, obligation, or denial of specific actions under specific contextual conditions. Although these policies expressed in Natural Language (NL) allow users to read and understand the allowed (or obliged or denied) operations on their data, the described policies cannot undergo automatic control of the actual use of the data by the entities that operate on them. This paper proposes an approach to systematically translate privacy statements related to data from NL into a controlled natural one, i.e., CNL4DSA to improve the machine processing. The methodology discussed in this work is based on a combination of standard Natural Language Processing (NLP) techniques, logic programming, and ontologies. The proposed technique is demonstrated with a prototype implementation and tested with policy examples. The system is tested with a number of data privacy policies from five different social network service providers. Predominantly, this work primarily takes into account two key aspects: (i) The translation of social networks' data privacy policy and (ii) the effectiveness and efficiency of the developed system. It is concluded that the proposed system can successfully and efficiently translate any common data policy based on an empirical analysis performed of the obtained results.