Research‎ > ‎Publications‎ > ‎

Privacy preserving trusted social feedback

Anirban Basu, Juan Camilo Corena, Shinsaku Kiyomoto, Stephen Marsh, Jaideep Vaidya, Guibing Guo, Jie, Zhang and Yutaka Miyake

In: The 29th ACM Symposium on Applied Computing (SAC) TRECK track, Gyeongju, Korea.

Year: 2014.

Abstract: With the growth of social networks, recommender systems have taken advantage of the social network graph structures to provide better recommendation. In this paper, we propose a privacy preserving trusted social feedback (TSF) system, in which users obtain feedback on questions or items from their friends. It is different from and independent of a typical recommender system because the responses from friends are not automated but tailored to specific questions. TSF can be used to complement the results from a recommender system. Our experimental prototype runs on the Google App Engine and utilises the Facebook social network graph. In our experimental evaluation, we have looked at users' perceptions of privacy and their trust in the prototype as well as the performances on the client side and the cloud side.

Fulltext: PDF.