Data-Driven QoE Analysis on Video Streaming in Mobile Networks

There is a substantial body of literature on analyzing Quality of Experience (QoE) of Video Streaming while there are few studies on standardizing QoE assessments. One of recent proposals on standardizing QoE of video streaming is video Mean Opinion Score (vMOS), which can model QoE of video streaming in 5 discrete grades. However, there are few studies on quantifying vMOS and investigating the relation between vMOS and other Quality of Service (QoS) parameters. In this paper, we address this concern by proposing a data-driven QoE analysis framework on video streaming QoE data. Moreover, we conduct extensive experiments on realistic dataset and verify the effectiveness of our proposed model. Our results show that vMOS is essentially affected by many QoS parameters such as initial buffering latency, stalling ratio and stalling times. Interestingly, we have found that a small set of QoS parameters play an important role in determining vMOS.