A User Experience Model for Privacy and Context Aware Over-the-Top (OTT) TV Recommendations

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

Conventional recommender systems provide personalized recommendations by collecting and retaining user data, relying on a centralized architecture. Hence, user privacy is undermined by the volume of information required to support the personalized experience. In this work, we propose a User Experience model witch allows the privacy preservation of a user by a decentralized architecture, enabling the Service Provider to offer recommendations without the need of storing individual user data. We advance the current state of the art by: i) Proposing a model of User Experience suitable for Persona-based recommendations; ii) Presenting a User Experience collection model able to enhance the user privacy towards the service provider while keeping the quality of her preferences predictions; and iii) Assessing the existence of the Persona profiles, which are needed for generating and addressing the recommendations. We perform several experiments using a real-world complete dataset from a medium-sized service provider, composed of more than 14,000 unique users and 33,000 content titles collected over a period of two years. We show that our architecture, in com- bination with our User Experience model, achieves the same results or better, in terms of rating prediction accuracy, as the state of the art systems, without sacrificing user’s privacy.
Close

Details

Conventional recommender systems provide personalized recommendations by collecting and retaining user data, relying on a centralized architecture. Hence, user privacy is undermined by the volume of information required to support the personalized experience. In this work, we propose a User Experience model witch allows the privacy preservation of a user by a decentralized architecture, enabling the Service Provider to offer recommendations without the need of storing individual user data. We advance the current state of the art by: i) Proposing a model of User Experience suitable for Persona-based recommendations; ii) Presenting a User Experience collection model able to enhance the user privacy towards the service provider while keeping the quality of her preferences predictions; and iii) Assessing the existence of the Persona profiles, which are needed for generating and addressing the recommendations. We perform several experiments using a real-world complete dataset from a medium-sized service provider, composed of more than 14,000 unique users and 33,000 content titles collected over a period of two years. We show that our architecture, in com- bination with our User Experience model, achieves the same results or better, in terms of rating prediction accuracy, as the state of the art systems, without sacrificing user’s privacy.
Original languageEnglish
Title of host publicationSIR: Workshop on Social Interaction-based Recommendation
PublisherAssociation for Computing Machinery
Publication date22 Oct 2018
Publication statusPublished - 22 Oct 2018
Publication categoryResearch
Peer-reviewedYes
ID: 284938132