Watch me playing, I am a professional A first study on video game live streaming M. Kaytoue 1 , A. Silva 1 , L. Cerf 1 , W. Meira Jr. 1 , C. Ra¨ ıssi 2 1 2 Belo Horizonte – Brazil Nancy – France Mining Social Network Dynamics @ WWW 2012 Lyon (France) - 16 April, 2012.
38
Embed
Watch me playing, I am a professional. A first study on video game live streaming
"Electronic-sport" (E-Sport) is now established as a new entertainment genre. More and more players enjoy streaming their games, which attract even more viewers. In fact, in a recent social study, casual players were found to prefer watching professional gamers rather than playing the game themselves. Within this context, advertising provides a significant source of revenue to the professional players, the casters (displaying other people's games) and the game streaming platforms. For this paper, we crawled, during more than 100 days, the most popular among such specialized platforms: Twitch.tv. Thanks to these gigabytes of data, we propose a first characterization of a new Web community, and we show, among other results, that the number of viewers of a streaming session evolves in a predictable way, that audience peaks of a game are explainable and that a Condorcet method can be used to sensibly rank the streamers by popularity. Last but not least, we hope that this paper will bring to light the study of E-Sport and its growing community. They indeed deserve the attention of industrial partners (for the large amount of money involved) and researchers (for interesting problems in social network dynamics, personalized recommendation, sentiment analysis, etc.).
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Watch me playing, I am a professionalA first study on video game live streaming
M. Kaytoue1, A. Silva1, L. Cerf1, W. Meira Jr.1, C. Raıssi2
1 2
Belo Horizonte – Brazil Nancy – France
Mining Social Network Dynamics @ WWW 2012Lyon (France) - 16 April, 2012.
Electronic Sports
Watching E-Sport on internet: a new entertainment?
Just like traditional sport but with video games
Professional commentators, sponsors, tournaments, etc.
Professional gamers streaming their games over internet
Spectators prefer to watch rather than playing themselves
A new Web community is growing
Widely using Web media such as FaceBook, Twitter, etc. and...
Live video game streaming platform gaining in popularity
Very active, important frequency of events
2 / 38Watch me playing, I am a professional
N
Events and tournaments
3 / 38Watch me playing, I am a professional
N
Social TV
4 / 38Watch me playing, I am a professional
N
ContributionStarting from Twitch.tv audience data
From September 29th, 2011 to January 09th, 2012
Every five minutes, get tuples of active streams(date, login, game, description, count, ...)
We propose a first characterization of this community
Quantitatively: audience, content length, etc.
Qualitatively: What games? Where? etc.
Early prediction of the audience
Ranking most popular professional gamers
Findings
Important for E-Sport actors – With nice perspectives of research
5 / 38Watch me playing, I am a professional
N
Outline
1 A first characterization of the E-Sport community
2 Predicting stream popularity
3 Ranking streamers
4 Conclusion and perspectives
6 / 38Watch me playing, I am a professional
N
A first characterization of the E-Sport community
Twitch data acquisition and description
Data
From September 29th, 2011 to January 09th, 2012
Every five minutes, get all of active streams and their audience
More than 24 millions of tuples
Cleaning: missing values, removing illegal streams (1.54%), etc.
field descriptiondate The date of crawling of the tuplelogin Unique identifier of a user/streamergame The game or topic of the stream
description A text description of the streamcount The number of viewers/spectators
watching the stream at a given time
7 / 38Watch me playing, I am a professional
N
A first characterization of the E-Sport community
Dataset Summary
Period of analysis Sept 29, 11 - Jan 9, 12#timestamps 28,292 (832 missing)
#views 27,120,337Length streamed 215.3 yearsLength watched 9,622.4 years
8 / 38Watch me playing, I am a professional
N
A first characterization of the E-Sport community
Views along the weeks (When?)
10000
20000
30000
40000
50000
60000
70000
Sun Mon Tue Wed Thu Fri Sat Sun 400
600
800
1000
1200
1400
1600
avg n
b o
f vie
wers
avg n
b o
f str
eam
ers
viewersstreamers
9 / 38Watch me playing, I am a professional
N
A first characterization of the E-Sport community
Geographic distribution (Where?)
10 / 38Watch me playing, I am a professional
N
A first characterization of the E-Sport community
Top 20 most popular games (What?)
Game Audience ReleaseStarCraft II 35.05% July 2010
Heroes of Newerth 8.89% May 2010League of Legends 8.19% Oct. 2009World of Warcraft 6.24% Nov. 2004Call of Duty: BO 3.88% Nov. 2010Street fighter 4 3.26% Apr. 2010
Star Wars (TOR) 2.98% Dec 2011The Elder Scrolls 2.36% Nov. 2011
MineCraft 2.03% Nov. 2011Rage 1.98% Oct. 2011
Marvel vs. Capcom 3 1.67% Feb. 2011Dota 2 (beta) 1.55% Sep. 2011Battlefield 3 1.39% Oct. 2011Warcraft III 1.22% July 2002Halo: Reach 1.20% Sept. 2010Mario Kart 7 1.18% Dec. 2011Dark Souls 1.10% Oct. 2011Zelda SS 1.05% Nov 2011
Gears of War 3 0.93% Sept. 2011Counter-Strike S 0.89 % Nov. 2004
Others 12.95%
11 / 38Watch me playing, I am a professional
N
A first characterization of the E-Sport community
Local game popularity (What?)%
of daily
audie
nce
Time (days)
BattlefieldCall of DutyDark SoulsDotaGears of WarCounter-StrikeHaloLeague of LegendsMarvel vs. CapcomMineCraftRageStarcraft IIStar WarsStreet FighterMario’sThe Elder ScrollsWarcraft IIIWorld of WarcraftZeldaHeroes of Newerth
12 / 38Watch me playing, I am a professional
N
A first characterization of the E-Sport community
Major E-Sport events (What?)
20000
30000
40000
50000
60000
70000
Oct. 11 Nov. 11 Dec. 11 Jan. 12
IEM N-YMLG Orlando
IGN Pro LeagueDreamHack Winter
Blizzard Cup
Home Story CupNASL S2 Finals
NE League S2 Grand Finals12 hours for charity
#views
13 / 38Watch me playing, I am a professional
N
A first characterization of the E-Sport community
Stream and Streamer characteristics
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
100
101
102
103
104
105
cu
mu
lative
(%
)
duration (min)
(a) Stream
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
100
101
102
103
104
105
106
cu
mu
lative
(%
)
duration (min)
(b) StreamerDuration of streams and aggregate duration of streamers
0
0.2
0.4
0.6
0.8
1
0 10 20 30 40 50 60 70 80 90 100
ag
reg
ate
vie
ws
stream rank
(c) Stream
0
0.2
0.4
0.6
0.8
1
0 10 20 30 40 50 60 70 80 90 100
ag
reg
ate
vie
ws
streamer rank
(d) StreamerStream and streamer audience
14 / 38Watch me playing, I am a professional
N
1 A first characterization of the E-Sport community
2 Predicting stream popularity
3 Ranking streamers
4 Conclusion and perspectives
Predicting stream popularity
MotivationCurrent Twitch recommendation strategy
New and interesting streams may take too long (or even never)to become visible
16 / 38Watch me playing, I am a professional
N
Predicting stream popularity
Motivation
Streaming sessions have a highly skewed popularity distribution,short duration, and slow popularity evolution.
0
0.2
0.4
0.6
0.8
1
0 10 20 30 40 50 60 70 80 90 100
ag
reg
ate
vie
ws
stream rank
(e)
0
0.1
0.2
0.3
0.4
0.5
0.6
0.7
0.8
0.9
1
100
101
102
103
104
105
cu
mu
lative
(%
)
duration (min)
(f)
0
0.05
0.1
0.15
0.2
0.25
0.3
0 2 4 6 8 10 12 14 16
pro
po
rtio
n o
f th
e o
ve
rall
ma
xim
al p
op
ula
rity
hours since the beginning of a session
average session for the top-100 streamers
(g)
Stream popularity, duration and popularity evolution
17 / 38Watch me playing, I am a professional
N
Predicting stream popularity
Idea
Predicting popularity using initial popularity records
100
101
102
103
104
105
100
101
102
103
104
105
po
pu
larity
aft
er
1 h
ou
r
popularity after ti minutes
(h) ti = 5 min.
100
101
102
103
104
105
100
101
102
103
104
105
po
pu
larity
aft
er
1 h
ou
r
popularity after ti minutes
(i) ti = 30 min.
Correlation between stream popularity after ti minutes and 1 hour
18 / 38Watch me playing, I am a professional
N
Predicting stream popularity
Correlation Varying ti
Correlation between popularity after ti minutes and 1 hour
0.5
0.6
0.7
0.8
0.9
1
5 10 15 20 25 30 8
9
10
11
12
13
14
corr
ela
tion
mean s
quare
d e
rror
ti (min)
corr.ε
19 / 38Watch me playing, I am a professional
N
Predicting stream popularity
Prediction Model
Model
log(pop(tf )) = β0 + β1 log(pop(ti )) + ε
Predicted vs. actual (based on popularity after ti minutes)
100
101
102
103
104
105
100
101
102
103
104
105
actu
al p
op
ula
rity
aft
er
1 h
ou
r
predicted popularity after 1 hour
(j) ti = 5 min.
100
101
102
103
104
105
100
101
102
103
104
105
actu
al p
op
ula
rity
aft
er
1 h
ou
r
predicted popularity after 1 hour
(k) ti = 30 min.
20 / 38Watch me playing, I am a professional
N
Predicting stream popularity
MSE Varying ti
MSE for different values of ti (minutes)
0.5
0.6
0.7
0.8
0.9
1
5 10 15 20 25 30 8
9
10
11
12
13
14
corr
ela
tion
mean s
quare
d e
rror
ti (min)
corr.ε
21 / 38Watch me playing, I am a professional
N
1 A first characterization of the E-Sport community
2 Predicting stream popularity
3 Ranking streamers
4 Conclusion and perspectives
Ranking streamers
Why rank streamers?
Interesting for
Spectators: Who to watch?
Sponsors: Who to support?
Teams: Who to recruit?
Gamers: Is my rival doing better?
Game editors: Is my game more popular than my concurrents?
23 / 38Watch me playing, I am a professional
N
Ranking streamers
Comparing two streamers
Audience depends of other streams active at the same time
Comparison of two streamers when they broadcast together
Example
On Nov. 10 19:00, WhiteRa is preferred to EG.IdrA. They arenot comparable with Mill.Stephano.
Raw audience is not a good measure of popularity because of:
daily/weekly variations of the number of viewers and sessions;
variations of the number of viewers along a session.
Idea for aggregating the preferences
Consider the streamers as candidates, the crawl points as votersand apply a Condorcet method that is known to be good forranking: Maximum Majority Voting.
25 / 38Watch me playing, I am a professional
N
Ranking streamers
Ranking the pairs of streamers
Three criteria with the following precedence:
c1 How often the first streamer is preferred to thesecond;