Factors Affecting the Performance of Recommender Systems in a Smart TV Environment

Abstract

The recommender systems are deployed on the Web for reducing cognitive overload. It uses different parameters, such as profile information, feedbacks, history, etc., as input and recommends items to a user or group of users. Such parameters are easy to predict and calculate for a single user on a personalized device, such as a personal computer or smartphone. However, watching the Web contents on a smart TV is significantly different from other connected devices. For example, the smart TV is a multi-user, lean-back supported device, and normally enjoyed in groups. Moreover, the performance of a recommender system is questionable due to the dynamic interests of groups in front of a smart TV. This paper discussed in detail the existing recommender system approaches in the context of smart TV environment. Moreover, it highlights the issues and challenges in existing recommendations for smart TV viewer(s) and presents some research opportunities to cope with these issues. The paper further reports some overlooked factors that affect the recommendation process on a smart TV. A subjective study of viewers’ watching behavior on a smart TV is also presented for validating these factors. Results show that apart from all technological advancement, the viewers are enjoying smart TV as a passive, lean-back device, and mostly used for watching live channels and videos on the big screen. Furthermore, in most households, smart TV is enjoyed in groups as a shared device which creates hurdles in personalized recommendations. This is because predicting the group members and satisfying each member is still an issue. The findings of this study suggest that for precise and relevant recommendations on smart TVs, the recommender systems need to adapt to the varying watching behavior of viewer(s).

Tailoring Recommendations to Groups of Viewers on Smart TV: A Real-Time Profile Generation Approach

“…The smart TV is a connected TV that brings further challenges in the form of security, privacy, irrelevant recommendations, and interactive user interfaces [3], [16]. The relevant recommendations can enhance the conversion rate up to some extent, which in turn contribute to e-commerce and e-business [22].…”

“…The relevant recommendations can enhance the conversion rate up to some extent, which in turn contribute to e-commerce and e-business [22]. Therefore, the appropriate and precise recommendations on smart TV may further contribute to not only user satisfaction [3], but also e-commerce. The highly interactive nature of smart TV is still reliant on traditional remote-control, which further creates issues in usability, searching, and browsing [3].…”

“…The rapid growth of web content makes it difficult to search and retrieve the content of interests and hence create the problem of cognitive and content overload [1]- [3]. To mitigate these issues, recommender systems play an important role [3]. The recommender systems are used to recommends related items to a user or group.…”

“…The focus of existing recommendation schemes on a smart TV is based on individual profiles, feedback, watching history, and location information. However, from smart TV perspectives, there may be groups of viewers having distinct ages, interests, tastes, etc., [3]. In such a case, the recommender system does not produce relevant recommendations.…”

“…This approach is widely used for group recommendation. However, in a smart TV environment, the profile merging strategies are not viable due to privacy leakages [3]. The exact identity of group members is still challenging due to privacy and security problems.…”