Real-time personalized content catering via viewer sentiment feedback: a QoE perspective

Multimedia content service and delivery have long been plagued by the difficulty in obtaining feedback on users' true quality of experience. Existing estimation methods do not adequately cover all relevant factors, whereas questionnaires are costly, time-consuming, and impossible to scale. In this work, we present a framework for estimating a viewer's reactions toward on-screen content in real time by capturing and analyzing his/her facial video, thus allowing up-to-date learning of the viewer's preferences to occur, enabling the content provider to serve the most desirable and relevant contents and advertisements. Experiments have shown that the proposed sentiment analysis method can predict the viewer's preferences with good accuracy.

Requirements and Goals

As discussed previously, in order to maintain good user QoE, content providers need to learn each individual user's preferences and cater his/her content suggestions and deliveries to such preferences so that the user can conveniently locate the desired content. Therefore, the requirements on the proposed content catering system are two-fold: •

It must be able to analyze in real time each user's individual reaction to on-screen content, so as to measure his/her affinity to the type of content shown.

•

It must be able to learn both long-term and short-term preferences of the user in order to deliver the most up-to-date and interesting content.