User Behaviour Analysis of a Video-On-Demand Service with a Wide Variety of Subjects and Lengths

This paper presents a detailed characterisation of user behaviour for a series of interactive video experiments over a 12 month period, in which we served popular sporting and musical content. In addition to generic VCR-like features, our custom-built Video-on-Demand application provides advanced interactivity features such as bookmarking. The dramatic impact of such functionality on how users consume content is studied and analysed. We discuss in detail how this user behaviour can be exploited by content distributors to improve user experience. Specifically, we study how simple dynamic bookmark placement and interactivity-aware content pre-fetching and replication can reduce the impact of highly interactive media on CDN performance.

show abstract

“…This is in accordance with previous work which found a positive correlation between session time and the number of pause operations [14].…”

Section: Interactionssupporting

confidence: 82%

“…Previous studies have found that the majority of inter-seek times are very short [14]. For educational content, inter-seek times have also been shown to be Poisson or Pareto distributed [3].…”

Section: Session Lengthsmentioning

confidence: 99%

Characterising and exploiting workloads of highly interactive video-on-demand

et al. 2008

View full text Add to dashboard Cite

show abstract

“…Vilas and Paneda et al modeled the user behavior of a VoD website [22], but they did not correlate the behavior with the QoE. In [24] and [10], a traffic analysis of a VoD system and an IPTV system was performed.…”

Section: Related Workmentioning

confidence: 99%

Inferring the QoE of HTTP video streaming from user-viewing activities

Mok

Chan

Wang

et al. 2011

Proceedings of the First ACM SIGCOMM Workshop on Measurements Up the Stack

142

View full text Add to dashboard Cite

HTTP video streaming, employed by most of the videosharing websites, allows users to control the video playback using, for example, pausing and switching the bit rate. These user-viewing activities can be used to mitigate the temporal structure impairments of the video quality. On the other hand, other activities, such as mouse movement, do not help reduce the impairment level. In this paper, we have performed subjective experiments to analyze userviewing activities and correlate them with network path performance and user quality of experience. The results show that network measurement alone may miss important information about user dissatisfaction with the video quality. Moreover, video impairments can trigger user-viewing activities, notably pausing and reducing the screen size. By including the pause events into the prediction model, we can increase its explanatory power.

show abstract

“…Plenty of research work [4][5][6] has been done by analyzing applications and contents that users interact with. However, these analysis tools are either embedded in applications or in the service provider's servers, which are not taking into account the new and powerful sensing capability of next generation mobile phones.…”

Section: Related Workmentioning

confidence: 99%

User Behavior Pattern Analysis and Prediction Based on Mobile Phone Sensors

Song¹,

Tang²,

Liu³

2010

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. More and more mobile phones are equipped with multiple sensors today. This creates a new opportunity to analyze users' daily behaviors and evolve mobile phones into truly intelligent personal devices, which provide accurate context-adaptive and individualized services. This paper proposed a MAST (Movement, Action, and Situation over Time) model to explore along this direction and identified key technologies required. The sensing results gathered from some mobile phone sensors were presented to demonstrate the feasibility. To enable always sensing while reducing power consumption for mobile phones, an independent sensor subsystem and a phone-cloud collaboration model were proposed. This paper also listed typical usage models powered by mobile phone sensor based user behavior prediction.

show abstract

User Behaviour Analysis of a Video-On-Demand Service with a Wide Variety of Subjects and Lengths

Cited by 49 publications

References 8 publications

Characterising and exploiting workloads of highly interactive video-on-demand

Characterising and exploiting workloads of highly interactive video-on-demand

Inferring the QoE of HTTP video streaming from user-viewing activities

User Behavior Pattern Analysis and Prediction Based on Mobile Phone Sensors

Contact Info

Product

Resources

About