ArticlePDF Available

An analysis of user behavior in online video streaming


Abstract and Figures

Understanding user behavior in online video streaming is essential to designing streaming systems which provide user-oriented service. However, it is challenging to gain insightful knowledge of the characteristics of user behavior due to its high volatility. To this end, the paper provides an extensive analysis of user behavior in online video streaming, based on a large scale trace database of online streaming video access sessions. We categorize user behaviors into multiple patterns and probe the relationship between them. Our work puts emphasis on the statistical characteristics of user behavior patterns. Particularly, this study uncovers that the behavior of one individual user in a video streaming session is not only related to the popularity level of the video, but also has strong correlation with the user's behaviors in previous streaming sessions.
Content may be subject to copyright.
An Analysis of User Behavior in Online Video Streaming
Fan Qiu
Department of Electrical Engineering and
Computer Science
Vanderbilt University, Nashville, TN 37212, USA
Yi Cui
Department of Electrical Engineering and
Computer Science
Vanderbilt University, Nashville, TN 37212, USA
Understanding user behavior in online video streaming is
essential to designing streaming systems which provide user-
oriented service. However, it is challenging to gain insightful
knowledge of the characteristics of user behavior due to its
high volatility. To this end, the paper provides an extensive
analysis of user behavior in online video streaming, based on
a large scale trace database of online streaming video access
sessions. We categorize user behaviors into multiple patterns
and probe the relationship between them. Our work puts
emphasis on the statistical characteristics of user behavior
patterns. Particularly, this study uncovers that the behavior
of one individual user in a video streaming session is not
only related to the popularity level of the video, but also
has strong correlation with the user’s behaviors in previous
streaming sessions.
Categories and Subject Descriptors
G.3 [Probability and Statistics]: Distribution Function;
H.2.8 [Database Management]: Database Applications—
Data Mining
General Terms
Measurement, Human Factors
Online video streaming, User behavior, Probability
Streaming video service offers a convenient and flexible
way of watching online videos, through which users could
play the video files simultaneously when the files are being
delivered from the server. Many streaming media websites
such as YouTube and MSN video provide millions of online
streaming videos. This gains online streaming video grow-
ing popularity among Internet users. With the development
Permission to make digital or hard copies of all or part of this work for
personal or classroom use is granted without fee provided that copies are
not made or distributed for profit or commercial advantage and that copies
bear this notice and the full citation on the first page. To copy otherwise, to
republish, to post on servers or to redistribute to lists, requires prior specific
permission and/or a fee.
VLS-MCMR’10 October 29, 2010, Firenze, Italy
Copyright 2010 ACM 978-1-4503-0166-4/10/10 ...$10.00.
of this technique, designers attempt to improve the qual-
ity of streaming service, so as to promote the level of user
satisfaction. To achieve this, it is essential to analyze the in-
formation of user behavior in streaming sessions supported
by the streaming servers [10]. These sessions essentially in-
volve a great amount of user interactions with streaming
system. There are various types of user behaviors related
to these interactions, such as play,stop,jump and pause.If
we understand the implications of the behaviors, we could
make the streaming server more efficient. For example, un-
derstanding behavior patterns helps us estimate the data
load on the server. In addition, the designer can adjust the
contents of the videos according to the response of the users.
Much research effort has been spent on investigating the
user behavior or client/server interactions in online video
streaming. However, user behaviors are not easy to be mod-
eled due to the following reasons: First, extraction of be-
havior information usually requires tedious effort on mining
the video trace datasets, which often contains huge amount
of data. Second, the high volatility of user behavior makes
it difficult to identify the behavior patterns and study the
relationship between them.
In order to analyze user behavior in online video stream-
ing, we use a large scale video trace database from MSN
video, which contains a great amount of video streaming
records retrieved in Year 2007 and Year 2008. Our study
consists of the following steps: 1) Mining the database and
retrieving the streaming sessions that contain information
of active user behavior; 2) Defining behavior patterns and
mapping user behaviors of the selected streaming sessions to
appropriate patterns; 3) Modeling the transitions between
behavior patterns by using a finite state machine (FSM); and
4) Analyzing several explanatory factors that carry signifi-
cant impact on user behavior. We mainly investigate session
groups consisting of consecutive streaming sessions. Each
group is corresponding to one individual user and one video
file. The time interval between two sessions in a group is rel-
atively small. Our research characterizes the user behaviors
of the streaming sessions from MSN database and uncov-
ers the relationship between the behavior patterns. We find
that user behavior is closely related to the popularity level
of a video. In addition, the behavior of an earlier session has
potential impact on the following sessions.
The rest of this paper is organized as follows: Sec. 2 in-
troduces the characteristics of our video trace database. In
Sec. 3 we propose the user behavior patterns and discuss the
transitions between them. We further analyze some factors
that have impact on user behaviors in this section. Sec. 4
0 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 1.8 2
x 104
File index
Number of Accesses (logrithm)
Figure 1: File Accesses
overviews some related work and indicates our contribution.
Sec. 5 concludes the paper and introduces the directions of
our future work.
Our database consists of trace records from about 5,000,000
video streaming sessions of Year 2007 and Year 2008. The
information of each streaming session is recorded as a ses-
sion entry. Because the raw database has much redundant
information, we first parse the database and keep the fol-
lowing items in each session entry: video ID, source data
rate, video length, player ID, session start time, buffer time,
buffer count and session duration. Here buffer time is the
total time spent on buffering the video file during a ses-
sion. Buffer count is the number of interruptions due to
data buffering during a session. In this section, we mainly
analyze the characteristics of the trace database and discuss
the extraction of sessions that are used in behavior analysis.
2.1 Video File Analysis
The database contains streaming sessions of approximately
76,000 online streaming video files. Each file is related to
some sessions. We first measure two metrics: the number
of accesses and the average duration ratio. The numbers
of accesses (during the entire time period monitored) of the
video files range from 1 to 158,000. The sorted results (nat-
ural logarithm of the number of accesses) of are presented
in Figure 1. Here we only keep the files that are accessed
more than 10 times. The other files are filtered because their
information may not be representative. The next important
metric is the average duration ratio of the streaming sessions
related to each video file. This value is an indicator of the
popularity level of a file, which will be discussed in Sec. 3. An
intuitive understanding of session duration is: users would
like to spend more time on a video if they are satisfied with
the streaming service, which leads to a longer session dura-
tion. However, it is unfair to directly compare the durations
of all the sessions, because different video files usaully have
different playback lengths. So we simply normalize the ses-
sion durations by computing the duration ratio (the ratio
between the session duration and the entire video file play-
back length). For each video file, we compute the median
duration ratio of its sessions. The sorted results are pre-
sented in Figure 2. This plot indicates that the video files
differ a lot: some files have a high popularity level, while
some files are less popular.
0 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 1.8 2
x 104
File Index
Median Duration Ratio
Figure 2: Median Session Duration Ratio
5 10 15 20 25 30 35 40
Number of Accesses of a User
Cumulative Distribution Function (CDF)
Figure 3: User Access Distribution
2.2 User Access Analysis
From the users’ perspective, we investigate the access ses-
sions of each individual user. Our database is divided into
many small groups. All the sessions in a group correspond to
one user ID and one video file ID. According to our measure-
ment, most groups contain only one session, which means
most users access a video file once. Because the groups
containing one session can barely provide any representa-
tive information for behavior analysis, we only explore the
characteristics of the groups with multiple (greater than 3)
streaming sessions. Figure 3 is the plot of the cumulative
distribution function (CDF) of the access rate. In Figure 4
we plot the cumulative distribution function of session du-
ration ratio.
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
Session Duration Ratio
Cumulative Distribution Function
Figure 4: User Access Duration Ratio
3.1 User Behavior Patterns
To study the characteristics of user behavior, we still use
the session groups mentioned in last section: all the sessions
belonging to the same user and same file. Therefore the
session entries in one group collectively describe a specified
user’s behaviors related to a particular video file. Because
we could hardly retrieve useful behavior information from
the groups with only one or two sessions, we filter out these
groups with small sizes.
A behavior pattern is defined according to two adjacent
streaming sessions in a group. We propose the following
seven behavior patterns: start,stop,jump forward,jump
backward,replay,pause and return. The definitions of these
patterns are as follows:
1. Start (B0): the beginning of an access to a video file.
The user has never accessed this file before. Here by
access” we mean a sequence of behavior patterns cor-
responding to a group. In other words, a group of
sessions belong to the same ”access”.
2. Stop (B1): the end of an access to a video file. After
this behavior, the user will not re-access the file during
the monitored period;
3. Jump forward (B2): compared to the end point of last
session in the timeline of the video, the user’s video
player jumps a certain distance towards the end of the
4. Jump backward (B3): compared to the end point of
last session in the timeline of the video, the user’s video
player jumps a certain distance towards the beginning
of the video file.
5. Replay (B4): the user finished playing the video before
this session, and he/she restarts to play the video from
the beginning point.
6. Pause (B5): the user’s video player starts from the
time point where it stopped in last session.
7. Return (B6): the user returns and keep playing the
Figure 5 is an illustration of several behavior patterns.
Now next important issue is how to identify patterns in the
session records. As we can see from the figure, if there is
a gap between two adjacent streaming sessions, a jump for-
ward pattern is generated. If there is an overlap between two
adjacent sessions, a jump backward pattern is generated. If
two adjacent sessions are well connected, a pause pattern is
generated. This pattern can be explained as: a user played
the video in an earlier session, then the video file was closed
at some point. In the following session, the user came back
and played the video from the point where he/she stopped
in last session.
According to the definitions of user behavior patterns, the
sessions within each group can be mapped to a sequence of
behavior patterns. Figure 6 is an example of translating a
group of sessions into behavior patterns. Here ”start time”
is the starting point of a session in the timeline of the video.
Similarly, ”end time” is the end point in the timeline.
Figure 5: User Behavior Patterns
Figure 6: Mapping Session Records to Behavior pat-
Since we have converted the session groups to sequences
of user behavior patterns, we can compute the distribution
of these patterns, which is shown in Figure 7. It is obvious
that in our experiment, jump forward and replay are the
two most frequent behavior patterns, and pa use is relatively
rare in these access sessions.
3.2 Transitions Between Patterns
To understand the relationship between behavior patterns,
we set out to study the transitions between them. From the
observations of the behavior pattern sequences, we find that
the patterns are transitive to each other. For example, in
Figure 6, the last replay pattern is followed by a jump back-
ward pattern in the following session. And this jump forward
pattern is then followed by a stop pattern in the next session.
This structure is similar to a finite state machine (FSM), if
we regard each behavior pattern as a state. Actually, the
seven user behavior patterns form a finite state space. So
Start Stop J_Forward J_Backward Replay Return Pause
4.5 x 104
Behavior Pattern
Number of Occurrences
Figure 7: Distribution of Behavior Patterns
Figure 8: Finite State Machine of User Behavior
we can construct a finite state machine to describe these
transitions. The sate machine is shown in Figure 8. The
transitions are indicated by the arrows. This FSM describes
how the transitions occur between the behavior patterns. In
addition, the FSM is featured by the following aspects: 1)
stop is always the last state of a state sequence, there is no
state following stop;2)start is the first state of a state se-
quence, so no state can move to start;3)paus e is always
followed by return.
We use transition probabilities to accurately describe the
transitions. Suppose current state is Si, and the next state
is Sj, so the transition probability between the two states
can be expressed as
Pij =Pr{Sj|Si}(1)
In Table 1 we list all the transition probabilities, which
are derived from the dataset consisting of the selected trace
groups (with group size greater than 3). Thus we can an-
alyze the transitions between the behavior patterns from a
statistical perspective.
In this table, the behavior patterns are represented by
variables B0 to B6. The variables on the first column repre-
sent current state. The variables on the first row represent
the following state. Notably, the probability from jump for-
ward to jump forward, and the probability from replay to
replay are relatively high. Here we need to clarify that this
transition table relies heavily on the trace database used. It
might not be accurate enough when applied to other trace
databases. However, it implies some implicit relationships
between the behavior patterns.
3.3 User Behavior Characteristics
In this section, we introduce some characteristics of user
behavior. We first focus on session duration. Intuitively,
session duration is easily affected by the inclination of the
user to the content of a video. To study this relationship, we
define a new variable: video popularity level. This metric
represents the popularity level of a file among its users. We
assume that it is strongly correlated to video content and
user inclination. Since the duration ratio of a session can
reflect a user’s satisfaction level, we use the median dura-
tion ratio of all the sessions related to a file to represent its
Table 1: Transition Probabilities Between User Be-
havior Patterns
B0 B1 B2 B3 B4 B5 B6
B0 0 0 0.399 0.127 0.421 00.054
B1 0 0 0 0 0 0 0
B2 00.308 0.494 0.104 0.065 00.031
B3 00.443 0.050 0.328 0.144 00.036
B4 00.302 0.068 0.030 0.589 00.011
B5 00.384 0.078 0.084 0.109 00.344
B6 0 0 0 0 0 1.000 0
0 20 40 60 80 100 120 140 160 180 200
Group Index
Session Duration Ratio
Video File
Popularity Level
Accumulative Sesseion
Duration Ratio
Figure 9: Video Popularity level and Session Dura-
tion Ratio
popularity level, which is a unique characteristic of this file.
In our experiment, we pick out about 200 session groups
with large group sizes. Here each group corresponds to one
video file and one user. We sort these groups by using video
popularity level. The result is represented by the solid line in
Figure 9. Then we measure the accumulative session dura-
tion ratio (represented by stars in the figure) of each group.
The accumulative group duration ratio is the sum of the du-
ration ratios of all the sessions in this group. If the sum is
greater than 1, it is set to 1. As the figure illustrates, the
accumulative duration ratio of a group with higher video
popularity level is possibly greater than that of a group with
lower level. So we argue that users usually spend more time
on a video with high popularity level.
Our study also reveals that a user’s behavior at a partic-
ular time point could be related to some other priori infor-
mation, such as the behavior patterns of the earlier access
sessions. For example, if a user has replayed the video for
several times, it is highly possible that he/she would play the
video in the following session(in the form of replay or jump
forward ),basedontheFSMdiscussedinlastsection.From
this phenomenon we could find some implications about the
interest level of the user. In addition, by analyzing the user
behaviors in a sequence of consecutive streaming sessions,
we can predict the user’s possible behaviors in the future
There have been many studies on mining user behavior
in web based applications, such as online advertisements [5],
multimedia streaming web search [1, 2, 11], and online so-
cial networks [12, 9, 8]. Attenberg, Cheng, Chatterjee et al.
[3, 6, 5] have studied the user behaviors involved in spon-
sored online advertisements. They modeled and predicted
the probabilities of clicks of the consumers. Agichtein, Brill,
and Dumais proposed that incorporating user behavior in-
formation can greatly improve the ordering accuracy of top
results in web search setting [1]. In [9], Maia et al. character-
ized and identified user behaviors in online social networks.
The researches by Benevenuto, Costa et al. [4, 7] focused on
analyzing user behaviors on the basis of video interactions.
Yu et al. introduced the user behavior and content access
patterns of large-scale video-on-demand systems [13]. They
further discussed the implications of user behavior on the
design of media streaming systems. The study of [14] in-
troduces the design and implementation of an optimization
system that enhances user experiences during web-based ac-
Different from the existing works, we categorize user be-
haviors during online video streaming into several behavior
patterns. By employing a finite state machine, we focus on
mining the statistical relationship between these patterns.
In this paper, we provide an extensive analysis of user
behavior in online video streaming, using streaming session
records from a large scale streaming video trace database.
Our contribution is in the following aspects: First, we an-
alyze the overall statistical characteristics access sessions
in the database. Second, we proposed seven user behavior
patterns and estimated the transition probabilities between
these patterns. Third, we introduce some factors that affect
user behavior, such as video popularity level and the behav-
iors in previous sessions. Currently, our study only uncovers
the characteristics of behavior patterns of consecutive ses-
One central challenge of user behavior analysis is estab-
lishing a quantitative model that accurately describes the
behaviors in video streaming. Base on the implicit charac-
teristics of user behavior analyzed in this paper, one direc-
tion of our future work is to design such a model to predict
the behaviors of an individual user or even the cooperative
behaviors of several users. Another branch of our research is
to apply user behavior model to user-oriented online stream-
ing system design.
We would like to thank Dr. Jin Li and Dr. Cheng Huang
of Microsoft Research to provide the video trace database.
[1] E. Agichtein, E. Brill, and S. Dumais. Improving web
search ranking by incorporating user behavior
information. In SIGIR ’06: Proceedings of the 29th
annual international ACM SIGIR conference on
Research and development in information retrieval,
pages 19–26, New York, NY, USA, 2006. ACM.
[2] E. Agichtein and Z. Zheng. Identifying ”best bet” web
search results by mining past user behavior. In KDD
’06: Proceedings of the 12t h ACM SIGKD D
international conference on Knowledge discovery and
data mining, pages 902–908, New York, NY, USA,
2006. ACM.
[3] J. Attenberg, S. Pandey, and T. Suel. Modeling and
predicting user behavior in sponsored search. In KDD
’09: Proceedings of the 15t h ACM SIG KDD
international conference on Knowledge discovery and
data mining, pages 1067–1076, New York, NY, USA,
2009. ACM.
[4] F. Benevenuto, F. Duarte, T. Rodrigues, V. A.
Almeida, J. M. Almeida, and K. W. Ross.
Understanding video interactions in youtube. In MM
’08: Proceeding of the 16th ACM international
conference on Multimed ia, pages 761–764, New York,
NY, USA, 2008. ACM.
[5] P. Chatterjee, D. Hoffman, and T. Novak. Modeling
the clickstream: Implications for web-based
advertising efforts. Marketing Science, 22(4):520–541,
[6] H. Cheng and E. Cant´u-Paz. Personalized click
prediction in sponsored search. In WSDM ’10:
Proceedings of the third ACM i ntern ational conferen ce
on Web search and data mining, pages 351–360, New
York, NY, USA, 2010. ACM.
[7] C. P. Costa, I. S. Cunha, A. Borges, C. V. Ramos,
M. M. Rocha, J. M. Almeida, and B. Ribeiro-Neto.
Analyzing client interactivity in streaming media. In
WWW ’04: Proceedings of the 13th internation al
conference on World Wide Web, pages 534–543, New
York, NY, USA, 2004. ACM.
[8] W. Lin, H. Zhao, and K. Liu. Incentive cooperation
strategies for peer-to-peer live multimedia streaming
social networks. Multimedia, IEEE Transactions on,
11(3):396 –412, april 2009.
[9] M. Maia, J. Almeida, and V. Almeida. Identifying user
behavior in online social networks. In SocialNets ’08:
Proceedings of the 1 st Workshop on Social N etwor k
Systems, pages 1–6, New York, NY, USA, 2008. ACM.
[10] Y.-C. Tu, J. Sun, M. Hefeeda, and S. Prabhakar. An
analytical study of peer-to-peer media streaming
systems. ACM Trans. Multimedia Comput. Commun.
Appl., 1(4):354–376, 2005.
[11] R. W. White and D. Morris. Investigating the
querying and browsing behavior of advanced search
engine users. In SIGIR ’ 07: Proceedings o f the 30th
annual international ACM SIGIR conference on
Research and development in information retrieval,
pages 255–262, New York, NY, USA, 2007. ACM.
[12] C. Wilson, B. Boe, A. Sala, K. P. Puttaswamy, and
B. Y. Zhao. User interactions in social networks and
their implications. In E uroSys 09: P roceedings of the
4th ACM European conference on Computer systems,
pages 205–218, New York, NY, USA, 2009. ACM.
[13] H. Yu, D. Zheng, B. Y. Zhao, and W. Zheng.
Understanding user behavior in large-scale
video-on-demand systems. In EuroSys ’06:
Proceedings of the 1 st ACM SI GOPS/EuroSys
European Conference on Computer Systems 2006,
pages 333–344, New York, NY, USA, 2006. ACM.
[14] D. Zhou, A. Chander, and H. Inamura. Optimizing
user interaction for web-based mobile tasks. In WWW
’10: Proceedings of the 19th inter nationa l con ference
on World wide web, pages 1333–1336, New York, NY,
USA, 2010. ACM.
... outlined byQiu & Cui (2010) "[f]irst, extraction of behavior information usually requires tedious effort on mining the video trace datasets, which often contains huge amount of data. Second, the high volatility of user behavior makes it difficult to identify the behavior patterns and study the relationship between them" (p. ...
In this dissertation, a case study is formed about the sport of rallying, and in particular, the World Rally Championship (WRC) and its media strategy. Traditionally, media rights have been sold to free-to-air television or pay-television networks in individual markets across the world. The premise became to sell the media rights to a sporting contest to the highest bidder, who would recoup their money through advertising and subscriptions to audiences. It is a system that brought great financial rewards to many sports. However, not all could make this model work. The WRC was one such sport as it was run over several days and in non-centralised geographic locations. It ensured the sport was not television-friendly and therefore could not generate significant media-driven financialisation. After a change in ownership, the WRC Promoter GmbH was formed and in 2013 a new media strategy was created, and then reinforced in 2018. They launched an over-the-top streaming service called WRC+ All Live. To do this, the WRC Promoter GmbH abandoned the notion of selling its product exclusively and primarily to a television partner, rather it went with a direct-to-consumer streaming service. The product available across the world without geoblocking restrictions. Along with the stream, the media rights are sold on a non-exclusive basis meaning that multiple media companies in the same marketplace can air the sport at the same time. It resulted in another shift for the WRC Promoter GmbH as they transitioned from a sports management concern to a sports media company with total responsibility for the media. The shift affected the fans as it changed their relationship with the sport and its media product and for sports media researchers, as the generally accepted sports rights model was abandoned. The case study, therefore, focuses aspects pertaining to decisions made, with regards to the streaming media product. The case study seeks to understand the effect that the change had on the economic aspects of the sport. As the media product has become of vital importance to the financial models of many sports, understanding how the WRC+ All Live and the effect on media-driven financialisation is the first area to be explored. It is followed by understanding how the shift from selling media rights to external broadcasters to that of becoming a media broadcaster in their own right and how that has affected the way the sport is operated. Finally, the way the fans engage with the sport under the new media delivery methods is understood. The streaming product had several effects on fan engagement. The first was that fans across the world could watch the same show at the same time. Secondly, the sport was delivered live for the first time, in what was a dramatic increase in programming, going from just a couple of hours of highlights per round, to more than 25 hours of live coverage. As the sport launched the product, it was unclear how the fans would react, and therefore understanding that reaction is important. The case of the WRC is important to understand, as technology and fan behaviours are changing which results in different opportunities for many niche sports in their media rights and media delivery models. The change to the media service and the WRC+ All Live is understood through multiple theoretical lenses. The first is that of the media-sport triangle. The triangle was conceived to help explain the financial and cultural success of some sports, with the relationship between sport, the media, and business. With popular sports on linear television, a culturally popular sport could be sold to television stations as they wanted the content and the audiences. Those audiences could be financialised through subscriptions or advertising, for example. However, the model must change for niche sports undertaking a direct-to-consumer model, where targeted audiences, and their attention can be commodified. The notions of digital plenitude are explored as internet-enabled technologies allow sports to undertake streaming media and with it, many barriers to delivery no longer exist. However, to create and distribute a streaming service requires a sport to rapidly professionalise and create an organisational culture to allow such a change to occur and become normalised in the organisation. Though the history of sports on television, a broadcast company has, generally, been the intermediary between the sport and the fans, providing their own services to create a product that was acceptable to these audiences. While elite sport has utilised professionals to play the game and to manage the sport, they now needed professionalise in new areas of sport media. Here, the WRC Promoter GmbH culturally enabled sport-entrepreneurial characteristics to take place that allowed a revolutionary media model to be created and normalised within its structures. Finally, the relationship with the fans is explored as without the fan having a willingness to pay for the service, and enjoying the mediated sport, the streaming product cannot obtain sufficient financial success. To ensure that sufficient reliable information could be found for the exploratory case study, a three-sided methodological approach was formed. The first method utilised was expert interviews. In total 27 expert interviews were conducted with key stakeholders in the sport, like senior managers, on-air talent and key people involved in media sales for the sport. Through these interviews, a complex and deep understanding of the decision-making processes could be formed. Importantly, the impact of the change of the media product to the sporting product itself could be understood, enabling a clear picture regarding the pressures, successes and necessary changes that were made to the sport to emerge. However, it was important to consolidate the validity of these findings through other methods. Observational research at nine WRC events over four years provided insight into how WRC events operated in different regions and how the media influenced the operation and standardisation of each event. Finally, desk research provided historical perspectives on decisions that were made prior to the research taking place, and to inform the research on decisions and attitudes throughout the execution of the case study. These theoretical perspectives and research techniques provided many key outcomes. It became clear that the transition away from traditional media strategies altered the power relationship between the sport, broadcasters and fans. The sport now guaranteed its position in every market across the world and its direct relationship with the fans. However, the culture and history of the sport played an important role in what actions the WRC Promoter GmbH could undertake. It was not a case of having a new owner, and therefore they could impose their own culture on the sport. To ensure fan enjoyment, the historical element of the event, the media product and the way the sport was run needed to be maintained. As the streaming market continues to develop, more niche sports seek to control their own media futures, and as promotion rights to sports are being bought and sold, the outcomes from the WRC+ All Live product can contain important lessons for other sports, and researchers into the future.
... Yu et al. (2006) employed early approaches to study content access patterns based on the observation of user groups. Qiu & Cui (2010) extended this research to the micro level of the individual and proposed that the behavior of users watching online videos can be categorized into seven patterns: start, stop, jump forward, jump backward, replay, pause and return. ...
Full-text available
Danmaku is an emerging comment design for videos that allows real-time, interactive comments from viewers. Danmaku increases viewers’ interaction with other viewers and streamers, thereby raising viewers’ loyalty and sense of belonging. Sending Danmaku comments demonstrates a higher degree of viewer involvement than traditional static comments below the videos. Therefore, it is necessary and meaningful to learn about viewers’ preferences by observing their behavior, as this may benefit the platform as well as the streamers. However, research on how the multimodal environment affects viewers’ behavior in sending Danmaku comments is quite limited. To fill this gap, we propose a new dataset and a deep neural network integrating multimodal information to predict whether viewers will send Danmaku comments (Deep Multimodal network for Danmaku Forecasting, DMDF) in order to evaluate the impact of the interaction of textual features, audio features and visual features on the behavior of viewers sending Danmaku comments. A series of experimental results based on a real dataset of 249657 samples from Bilibili (a leading Chinese video streaming Website) demonstrate the effectiveness of the proposed DMDF and the helpfulness of all modalities, especially visual and acoustic features, in behavior forecasting. DMDF with the multimodal squeeze-and-excitation (MSE) module we proposed achieves 90.14% on accuracy and 83.60% on F1-score, and it reveals the extent to which a user-generated video can influence viewers to send Danmaku comments, which helps predict viewers’ online viewing behavior. Furthermore, our model contributes to the current work on the video understanding task.
... Previous researches on VOD mainly focused on improving the technology of VOD service by user behavior analysis [11,13,15] and popularity analysis [6,10]. This study will explore the cultural differences of VOD user experience and shed light on user experience study of mobile VOD service. ...
Conference Paper
Full-text available
The objective of this study is to investigate the cross-cultural differences of user experience on mobile VOD service between Chinese and German users. The goal was to provide insight for culturally adaptive mobile VOD service design. This study focused on two aspects of user experience, which are content preference and interface preference. A questionnaire survey was conducted with 20 respondents to find out what kind of content users prefer (i.e. content preference), and a user experiment was carried out with 8 participants to explore users’ preference of VOD interface on mobile devices (i.e. interface preference). The results indicated that Chinese users spend more time on videos uploaded by individual users than German users. Besides, users from both cultures prefer the interface with more literal description to interface full of pictures. At last, suggestions for VOD service providers in both cultures are provided.
... (3) The clients have homoge neous resources. More recent characterization studies [9,10], however, reveal that the actual workload is more complex and dynamic. In particular, the workload contains many interac tive operations, and a user may access an object from a point other than the beginning and may stop before the end. ...
Conference Paper
Full-text available
The design of interactive Video-on-Demand (VOD) systems is highly complicated when scalable stream merging is used. Support of requests under the Near Video-on-Demand (NVOD), where not all requests are serviced immediately, introduces additional complications. We develop an overall solution for designing interactive NVOD systems when stream merging is employed. The proposed solution supports user interactions with short response times and low rejection probabilities. In addition, we propose an efficient dynamic stream allocation policy and use a sophisticated client-side cache management policy. We analyze system performance, through extensive simulation, using realistic workload under different levels of user interactivity.
... In [Mongy 2007], the K-means technique is used to retrieve and cluster user behaviors using a Markovian model based on a movie trailer database. Another work [Qiu and Cui 2010] probes the relationship between several types of user behavior and uncovers that the behavior of one individual user in a video streaming session has strong correlation with the user's behaviors in previous streaming sessions. While these works tell us more about user behavior, their results are not particularly helpful in designing our rate allocation algorithms. ...
A big portion of Internet traffic nowadays is video. A good understanding of user behavior in online Video-on-Demand (VoD) systems can help us design, configure and manage video content distribution. With the help of a major VoD service provider, we conducted a detailed study of user behavior watching streamed videos over the Internet. We engineered the video player at the client side to collect user behavior reports for over 540 million sessions. In order to isolate the possible effect of session quality of experience (QoE) on user behavior, we use only the sessions with perfect QoE, and leave out those sessions with QoE impairments (such as freezes). Our main finding is that users spend a lot of time browsing: viewing part of one video after another, and only occasionally (around 20% of the time) watching a video to its completion. We consider seek (jump to a new position of the video) as a special form of browsing - repeating partial viewing of the same video. Our analysis leads to a user behavior model in which a user transitions through a random number of short views before a longer view, and repeats the process a random number of times. This model can be considered an extension, and a more detailed alternative to the closed queueing network formulation introduced by Wu et al [1]. As an application of our user behavior model, we use it to measure video popularity. We study the similarity of our approach to subjective evaluation and simple view count based metric, and conclude our approach gives results closer to subjective evaluation.
With significant growth in video streaming services, coupled with widespread use of traffic encryption, network operators are faced with the challenge of monitoring Key Performance Indicators (KPI) needed to detect quality impairments and drive Quality of Experience (QoE) management mechanisms. Though literature suggests that QoE/KPIs can be inferred from encrypted network traffic using machine learning (ML) methods, most studies published thus far fail to account for frequent viewer interactions, such as pauses, seeking forward/backward, or video abandonment. Such playback-related interactions inherently impact traffic patterns used as input for ML–based KPI estimation models. In this paper, we investigate to what extent network operators can monitor application-layer KPIs considering realistic user interactions, focusing on the use-case of a popular streaming platform with videos streamed to mobile devices. We first investigate the impact of user interactions (pause, seek forward, and abandonment) on the performance of both session-based and real-time KPI classification models trained on datasets that do not contain interactions. Secondly, we systematically evaluate the performance of KPI estimation models trained on datasets including specific sets of interactions to determine which types of interactions need to be included in the model training procedure in order to be applicable for realistic streaming sessions.
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 Qrator , 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.
Internet access has changed media communication forever and reshaped the business models of mobile carriers and Pay-TV companies alike. A growing number of studies have addressed this trend emerging in the media and entertainment industry. However, a substantial part of this research lacks systemization and categorization and there is a tendency to start anew with every study. As such, it is imperative to assess current knowledge in this area. Today, consumers are increasingly expecting personalized content at their fingertips anytime and anywhere as companies such as Uber and Airbnb redefine on-demand access to services. Because of it, entertainment and media companies along with the entire value chain from content production to aggregation and distribution are undergoing unprecedented change in this direct-to-consumer (D2C) environment. This shift in media consumption is driven primarily by the rise of Internet-driven, over-the-top (OTT) streaming platforms that bypass the traditional distribution channels. Accordingly, a review of current literature spanning 2007 to 2021 identified twelve factors influencing the adoption of OTT platforms. This literature review is the first one in the domain of over-the-top media to identify the influencing factors across the streaming platforms. The factors included content, price, flexibility, convenience (perceived ease of use), perceived usefulness, perceived enjoyment (hedonic motivation), desire to be freed from any constraint, entertainment value, socialization, culture inclusion, binge-watching, and self-efficacy that leads to the adoption of OTT streaming platforms.
Conference Paper
Social networking applications are one of the main sources of content in the current internet, where currently the most of the traffic is composed of transferring text and still images. In the near future it is expected that members (users) of social networks will move to richer media, generating and consuming a large variety of multimedia content within these networks, thus Future Internet should be prepared to handle such demands. The underlying user community drives the media consumption and determines the network conditions in such cases. Proper modeling of the user community within such a system would make possible the accurate evaluation of the impact of these applications. Content generated by live media sharing communities differs from stored video content available online for streaming or download (e.g., NetFlix, YouTube, etc.) and the underlying user pattern is different, as well. In this paper we identify the key aspects of user communities in live multimedia distribution systems and investigate statistical features of each aspect. We have collected and analysed data from different live video portals and show that the statistical features of different portals follow similar trends.
Conference Paper
Full-text available
The top web search result is crucial for user satisfaction with the web search experience. We argue that the importance of the relevance at the top position necessitates special handling of the top web search result for some queries. We propose an effective approach of leveraging millions of past user interactions with a web search engine to automatically detect "best bet" top results preferred by majority of users. Interestingly, this problem can be more effectively addressed with classification than using state-of- the-art general ranking methods. Furthermore, we show that our general machine learning approach achieves precision comparable to a heavily tuned, domain-specific algorithm, with significantly higher coverage. Our experiments over millions of user interactions for thousands of queries demonstrate the effectiveness and robustness of our techniques.
Conference Paper
Full-text available
Sponsored search is a multi-billion dollar business that generates most of the revenue for search engines. Predicting the probability that users click on ads is crucial to sponsored search because the prediction is used to influence ranking, filtering, placement, and pricing of ads. Ad ranking, filtering and placement have a direct impact on the user experience, as users expect the most useful ads to rank high and be placed in a prominent position on the page. Pricing impacts the advertisers' return on their investment and revenue for the search engine. The objective of this paper is to present a framework for the personalization of click models in sponsored search. We develop user-specific and demographic-based features that reflect the click behavior of individuals and groups. The features are based on observations of search and click behaviors of a large number of users of a commercial search engine. We add these features to a baseline non-personalized click model and perform experiments on offline test sets derived from user logs as well as on live traffic. Our results demonstrate that the personalized models significantly improve the accuracy of click prediction.
Conference Paper
Full-text available
We show that incorporating user behavior data can significantly improve ordering of top results in real web search setting. We examine alternatives for incorporating feedback into the ranking process and explore the contributions of user feedback compared to other common web search features. We report results of a large scale evaluation over 3,000 queries and 12 million user interactions with a popular web search engine. We show that incorporating implicit feedback can augment other features, improving the accuracy of a competitive web search ranking algorithms by as much as 31% relative to the original performance.
Conference Paper
Full-text available
One way to help all users of commercial Web search engines be more successful in their searches is to better understand what those users with greater search expertise are doing, and use this knowledge to benefit everyone. In this paper we study the interaction logs of advanced search engine users (and those not so advanced) to better understand how these user groups search. The results show that there are marked differences in the queries, result clicks, post-query browsing, and search success of users we classify as advanced (based on their use of query operators), relative to those classified as non-advanced. Our findings have implications for how advanced users should be supported during their searches, and how their interactions could be used to help searchers of all experience levels find more relevant information and learn improved searching strategies.
Multimedia social networks have become an emerging research area, in which analysis and modeling of the behavior of users who share multimedia are of ample importance in understanding the impact of human dynamics on multimedia systems. In peer-to-peer live-streaming social networks, users cooperate with each other to provide a distributed, highly scalable and robust platform for live streaming applications. However, every user wishes to use as much bandwidth as possible to receive a high-quality video, while full cooperation cannot be guaranteed. This paper proposes a game-theoretic framework to model user behavior and designs incentive-based strategies to stimulate user cooperation in peer-to-peer live streaming. We first analyze the Nash equilibrium and the Pareto optimality of two-person game and then extend to multiuser case. We also take into consideration selfish users' cheating behavior and malicious users' attacking behavior. Both our analytical and simulation results show that the proposed strategies can effectively stimulate user cooperation, achieve cheat free, attack resistance and help to provide reliable services.
Conference Paper
Implicit user feedback, including click-through and subsequent brows- ing behavior, is crucial for evaluating and improving the quality of results returned by search engines. Several recent studies (1, 2, 3, 13, 25) have used post-result browsing behavior including the sites visited, the number of clicks, and the dwell time on site in order to improve the ranking of search results. In this paper, we first study user behavior on sponsored search results (i.e., the advert isements displayed by search engines next to the organic results), and compare this behavior to that of organic results. Second, to exploit post-result user behavior for better ranking of sponsored results, we focus on identifying patterns in user behavior and predict expected on-site ac- tions in future instances. In particular, we show how post-r esult be- havior depends on various properties of the queries, advertisement, sites, and users, and build a classifier using properties suc h as these to predict certain aspects of the user behavior. Additional ly, we de- velop a generative model to mimic trends in observed user activ- ity using a mixture of pareto distributions. We conduct experiments based on billions of real navigation trails collected by a ma jor search engine's browser toolbar.
Conference Paper
ABSTRACT This paper seeks understanding the user behavior in a social net- work created essentially by video interactions. We present a char- acterization of a social network created by the video interactions among users on YouTube, a popular social networking video shar- ing system. Our results uncover typical user behavioral patterns as well as show,evidences of anti-social behavior such as self- promotion,and other types of content pollution. Categories and Subject Descriptors H.3.5 [Online Information Services]: Web-based services; J.4 [Computer Applications]: Social and behavioral sciences General Terms Human factors, Measurement, Videos Keywords video response, social networks, promotion
Conference Paper
This paper describes the design and prototype implementation of MIntOS (Mobile Interaction Optimization System), a system for improving mobile interaction in web-based activities. MIntOS monitors users' interactions both for gathering interaction history and for the runtime construction of interaction context. A simple approach based on interaction burstiness is used to break interaction sequences into Trails, which approximates user tasks. Such Trails are used to generate rules for online, context-sensitive prediction of future interaction sequences. Predicted user interaction sequences are then optimized to reduce the amount of user input and user wait time using techniques such as interaction short-cuts, automatic text copying and form-filling, as well as page pre-fetching. Such optimized interaction sequences are, at real-time, recommended to the user through UI enhancements in a non-intrusive manner.
Conference Paper
Video-on-demand over IP (VOD) is one of the best-known exam- ples of "next-generation" Internet applications cited as a goal by networking and multimedia researchers. Without empirical data, researchers have generally relied on simulated models to drive their design and developmental efforts. In this paper, we present one of the first measurement studies of a large VOD system, using data covering 219 days and more than 150,000 users in a VOD system deployed by China Telecom. Our study focuses on user behav- ior, content access patterns, and their implications on the design of multimedia streaming systems. Our results also show that when used to model the user-arrival rate, the traditional Poisson model is conservative and overestimates the probability of large arrival groups. We introduce a modified Poisson distribution that more accurately models our observations. We also observe a surpris- ing result, that video session lengths has a weak inverse correlation with the video's popularity. Finally, we gain better understanding of the sources of video popularity through analysis of a number of internal and external factors.
Conference Paper
Social networks are popular platforms for interaction, communication and collaboration between friends. Researchers have recently proposed an emerging class of applications that leverage relationships from social networks to improve security and performance in applications such as email, web browsing and overlay routing. While these applications often cite social network connectivity statistics to support their designs, researchers in psychology and sociology have repeatedly cast doubt on the practice of inferring meaningful relationships from social network connections alone. This leads to the question: Are social links valid indicators of real user interaction? If not, then how can we quantify these factors to form a more accurate model for evaluating socially-enhanced applications? In this paper, we address this question through a detailed study of user interactions in the Facebook social network. We propose the use of interaction graphs to impart meaning to online social links by quantifying user interactions. We analyze interaction graphs derived from Facebook user traces and show that they exhibit significantly lower levels of the "small-world" properties shown in their social graph counterparts. This means that these graphs have fewer "supernodes" with extremely high degree, and overall network diameter increases significantly as a result. To quantify the impact of our observations, we use both types of graphs to validate two well-known social-based applications (RE and SybilGuard). The results reveal new insights into both systems, and confirm our hypothesis that studies of social applications should use real indicators of user interactions in lieu of social graphs.