Qrator: An Interest-Aware Approach to ABR Streaming Based on User Engagement

Abstract

Conventional approaches to adaptive bitrate (ABR) streaming fail to further improve the quality of experience (QoE) as they are indifferent to video semantics and user behaviors by focusing solely on the network conditions. These ABR schemes cannot enhance the perceptual video quality as they neglect the users’ varying degree of interest (DoI) over video sections and may experience QoE degradation due to frequent rebuffers caused by user behaviors such as selectively watching the interesting sections. To this end, this article proposes <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Qrator</i> , which is the very first attempt to utilize timestamps and likes as user engagement data to infer users’ genuine interests and further elevate the user-perceived QoE. Based on timestamps and likes in video comments, Qrator improves the overall QoE by considering DoI variations and user behaviors in performing interest-aware rate adaptation and prefetching. Qrator can be widely applied to conventional ABR approaches without significantly modifying their implementations. Evaluation results show that Qrator can heighten the bitrates of user interest sections without degrading the average bitrate. Furthermore, applying Qrator under user behavior patterns can reduce the rebuffering ratio and the number of rebuffers by 32% and 31%, respectively, while maintaining other QoE metrics to a similar extent.