Author
Aycı, G., Şensoy, Murat, Özgür, A., Yolum, P.
Publication Date
2023
Publication Place
-
International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Subject
Explainability, Online social networks, Privacy
Type
Document
Language
English
Digital
Yes
Manuscript
No
Library
Özyeğin University
Library Asset ID
1548-8403
Record ID
9fbf9094-cf7a-4e80-9f43-8d25dfc561fe
Library Location
Computer Science
Date
2023
Notes
Ministerie van Onderwijs, Cultuur en Wetenschap ; Nederlandse Organisatie voor Wetenschappelijk Onderzoek ; TÜBİTAK
Sample Text
Privacy assistants help users manage their privacy online. Their tasks could vary from detecting privacy violations to recommending sharing actions for content that the user intends to share. Recent work on these tasks are promising and show that privacy assistants can successfully tackle them. However, for such privacy assistants to be employed by users, it is important that these assistants can explain their decisions to users. Accordingly, this work develops a methodology to create explanations of privacy. The methodology is based on identifying important topics in a domain of interest, providing explanation schemes for decisions, and generating them automatically. We apply our proposed methodology on a real-world privacy data set, which contains images labeled as private or public to explain the labels.
