Video stream quality impacts viewer behavior: inferring causality using quasi-experimental designs

  title={Video stream quality impacts viewer behavior: inferring causality using quasi-experimental designs},
  author={S. Shunmuga Krishnan and Ramesh K. Sitaraman},
  journal={IEEE/ACM Trans. Netw.},
The distribution of videos over the Internet is drastically transforming how media is consumed and monetized. Content providers, such as media outlets and video subscription services, would like to ensure that their videos do not fail, start up quickly, and play without interruptions. In return for their investment in video stream quality, content providers expect less viewer abandonment, more viewer engagement, and a greater fraction of repeat viewers, resulting in greater revenues. The key… 

Suffering from buffering? Detecting QoE impairments in live video streams

A measurement study of adaptive bitrate video streaming for a large-scale live event that was streamed by hundreds of thousands of viewers in the United States, and designs and implements a Principal Component Analysis (PCA) based technique to detect live video QoE impairments in real-time.

Network performance: Does it really matter to users and by how much?

  • R. Sitaraman
  • Computer Science
    2013 Fifth International Conference on Communication Systems and Networks (COMSNETS)
  • 2013
This work hypothesizes that the availability of large amounts of performance and behavioral data and the development of novel analytical tools will finally put the users back at the center of network performance research, revolutionizing both how networks are architected for performance and how business models are evolved for real-world networks.

Understanding viewing engagement and video quality in a large-scale mobile video system

A user engagement prediction framework is designed to let content providers predict how long viewers will remain in video sessions with specific video quality metrics, and several counter-intuitive relationships are identified, based on the large-scale trace data from a famous IPTV provider.

Scoring High: Analysis and Prediction of Viewer Behavior and Engagement in the Context of 2018 FIFA WC Live Streaming

This paper analyzes a unique dataset consisting of more than a million 2018 FIFA World Cup mobile live streaming sessions, collected at a large national public broadcaster, to model viewer engagement over the course of a soccer match, and shows that client counts follow very similar patterns of change across all matches.

Understanding the causal impact of the video delivery throughput on user engagement

  • Qingxia Li
  • Computer Science
    Multimedia Tools and Applications
  • 2018
It is pointed out that crossing AS (Autonomous System) borders does not necessarily imply a higher likelihood of being a problem session, as only 22% of the AS pairs show a statistically significant impact on video download speed.

Analyzing the potential benefits of CDN augmentation strategies for internet video workloads

Surprisingly, significant amount of synchronous viewing behavior for Video On Demand (VOD) content is found, which makes hybrid P2P-CDN approach feasible for VOD and new strategies for CDNs to reduce their infrastructure costs are suggested.

Modeling large-scale live video streaming client behavior

An in-depth characterization and modeling of client behavior during the live streaming of the 2018 FIFA World Soccer Cup is presented, and a simple hierarchical model is proposed to describe the typical behavior of individual clients both at the session and video bitrate adaptation layers.

Inferring Streaming Video Quality from Encrypted Traffic: Practical Models and Deployment Experience

This paper develops models that infer quality metrics (i.e., startup delay and resolution) for encrypted streaming video services and develops a single composite model that works for a range of different services, as opposed to just a single service.

Joint effect of stalling and presentation quality on the quality-of-experience of streaming videos

A streaming video dataset is developed that contains compressed videos with different distortion levels as well as playback stalling events, and a subjective user study is performed to measure the Quality-of-Experience (QoE) of these videos.

An Engagement Model Based on User Interest and QoS in Video Streaming Systems

The proposed model has potential for designing QoE-oriented scheduling strategies in various network scenarios, especially in the fog computing context and reaches an improvement in accuracy over the baseline model which only considers QoS factors.



Understanding the impact of video quality on user engagement

As the distribution of the video over the Internet becomes main- stream and its consumption moves from the computer to the TV screen, user expectation for high quality is constantly increasing. In

I tube, you tube, everybody tubes: analyzing the world's largest user generated content video system

This paper analyzed YouTube, the world's largest UGC VoD system, and provided an in-depth study of the popularity life-cycle of videos, the intrinsic statistical properties of requests and their relationship with video age, and the level of content aliasing or of illegal content in the system.

A case for a coordinated internet video control plane

Using measurement-driven insights, a case is made for a video control plane that can use a global view of client and network conditions to dynamically optimize the video delivery in order to provide a high quality viewing experience despite an unreliable delivery infrastructure.

Defining user perception of distributed multimedia quality

A model that assesses quality variation from three distinct levels: the network, the media and the content levels; and from two views: the technical and the user perspective shows that a significant reduction in frame rate does not proportionally reduce the user's understanding of the presentation independent of technical parameters.

The effects of jitter on the peceptual quality of video

It is found that jitter degrades perceptual quality nearly as much as does packet loss, and that perceptual quality degrades sharply even with low 1eveIs of jitter or packet loss as compared to perceptual quality for perfect video.

An analysis of live streaming workloads on the internet

It is found that Internet streaming does reach a wide audience, often spanning hundreds of AS domains and tens of countries, and that small streams also have a diverse audience.

Quality of experience in distributed interactive multimedia environments: toward a theoretical framework

The results present the first deep study to model the multi-facet QoE construct, map the QoS-QoE relationship, and capture the human-centric quality modalities in the context of DIMEs.

Quantifying Skype user satisfaction

This work proposes a model, geared to Skype, but generalizable to other VoIP services, to quantify VoIP user satisfaction based on a rigorous analysis of the call duration from actual Skype traces, and produces a unique User Satisfaction Index (USI) derived from the model.

A transport layer for live streaming in a content delivery network

The design choices made during the evolution of Akamai's CDN for streaming media are discussed to ensure the network's scalability, quality of delivered content, and reliability while keeping costs low.

Causal discovery in social media using quasi-experimental designs

Three different QEDs are applied to demonstrate how one can gain a causal understanding of a social media system and the conclusions drawn can have threats to their validity, but it is shown how one could carefully construct sophisticated designs to overcome some of those threats.