Towards a Privacy Respecting Image-based User Profiling Component

Abstract

This paper explores the development of a framework for content-aware user profiling, studying how image producers and consumers can be better understood and consequently better served through services such as matchmaking and friend recommendations. User interests and similarities are extracted and analyzed on the edge employing state of the art CNN models over user images for the tasks of classification, as well as, building latent user representations from personal media content. A private-by-design approach is employed through the development and deployment of models on-device, avoiding the need for communicating personal data to a central service. Experimental results show that user profiling can provide accurate ranking of the users' interests and meaningful user associations through profile similarity.

SentiTrust: A New Trust Model for Decentralized Online Social Media

“…Profile Similarity (PS) is a score that measures how similar two users are. User profiling can adopt multiple techniques, such as those based on the images stored on a user device [35], or on other arbitrary features [36]. After profiling the users, a similarity metric is computed to understand to what extent two users share common interests.…”