Watch me playing, I am a professional A first study on video game - - PowerPoint PPT Presentation

▶
watch me playing i am a professional
SMART_READER_LITE
LIVE PREVIEW

Watch me playing, I am a professional A first study on video game - - PowerPoint PPT Presentation

Aug 13, 2022 202 likes •595 views

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 ssi 2 1 2 Belo Horizonte Brazil Nancy France Mining Social Network Dynamics @ WWW 2012

slide-1
SLIDE 1

Watch me playing, I am a professional

A first study on video game live streaming

  • M. Kaytoue1, A. Silva1, L. Cerf1, W. Meira Jr.1, C. Ra¨

ıssi2 1 2

Belo Horizonte – Brazil Nancy – France Mining Social Network Dynamics @ WWW 2012 Lyon (France) - 16 April, 2012.

slide-2
SLIDE 2

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 / 38 Watch me playing, I am a professional

slide-3
SLIDE 3

Events and tournaments

3 / 38 Watch me playing, I am a professional

slide-4
SLIDE 4

Social TV

4 / 38 Watch me playing, I am a professional

slide-5
SLIDE 5

Contribution

Starting 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 / 38 Watch me playing, I am a professional

slide-6
SLIDE 6

Outline

1 A first characterization of the E-Sport community 2 Predicting stream popularity 3 Ranking streamers 4 Conclusion and perspectives

6 / 38 Watch me playing, I am a professional

slide-7
SLIDE 7

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 description date The date of crawling of the tuple login Unique identifier of a user/streamer game The game or topic of the stream description A text description of the stream count The number of viewers/spectators watching the stream at a given time

7 / 38 Watch me playing, I am a professional

slide-8
SLIDE 8

A first characterization of the E-Sport community

Dataset Summary

Period of analysis Sept 29, 11 - Jan 9, 12 #timestamps 28,292 (832 missing) #logins 129,332 #games 17,749 #tuples 24,018,644 #illegal tuples 369,470 (1.54%) #sessions 1,175,589 #views 27,120,337 Length streamed 215.3 years Length watched 9,622.4 years

8 / 38 Watch me playing, I am a professional

slide-9
SLIDE 9

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 nb of viewers avg nb of streamers viewers streamers 9 / 38 Watch me playing, I am a professional

slide-10
SLIDE 10

A first characterization of the E-Sport community

Geographic distribution (Where?)

10 / 38 Watch me playing, I am a professional

slide-11
SLIDE 11

A first characterization of the E-Sport community

Top 20 most popular games (What?)

Game Audience Release StarCraft II 35.05% July 2010 Heroes of Newerth 8.89% May 2010 League of Legends 8.19%

  • Oct. 2009

World of Warcraft 6.24%

  • Nov. 2004

Call of Duty: BO 3.88%

  • Nov. 2010

Street fighter 4 3.26%

  • Apr. 2010

Star Wars (TOR) 2.98% Dec 2011 The Elder Scrolls 2.36%

  • Nov. 2011

MineCraft 2.03%

  • Nov. 2011

Rage 1.98%

  • Oct. 2011

Marvel vs. Capcom 3 1.67%

  • Feb. 2011

Dota 2 (beta) 1.55%

  • Sep. 2011

Battlefield 3 1.39%

  • Oct. 2011

Warcraft III 1.22% July 2002 Halo: Reach 1.20%

  • Sept. 2010

Mario Kart 7 1.18%

  • Dec. 2011

Dark Souls 1.10%

  • Oct. 2011

Zelda SS 1.05% Nov 2011 Gears of War 3 0.93%

  • Sept. 2011

Counter-Strike S 0.89 %

  • Nov. 2004

Others 12.95% 11 / 38 Watch me playing, I am a professional

slide-12
SLIDE 12

A first characterization of the E-Sport community

Local game popularity (What?)

% of daily audience Time (days) Battlefield Call of Duty Dark Souls Dota Gears of War Counter-Strike Halo League of Legends Marvel vs. Capcom MineCraft Rage Starcraft II Star Wars Street Fighter Mario’s The Elder Scrolls Warcraft III World of Warcraft Zelda Heroes of Newerth

12 / 38 Watch me playing, I am a professional

slide-13
SLIDE 13

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-Y MLG Orlando IGN Pro League DreamHack Winter Blizzard Cup Home Story Cup NASL S2 Finals NE League S2 Grand Finals 12 hours for charity #views

13 / 38 Watch me playing, I am a professional

slide-14
SLIDE 14

A first characterization of the E-Sport community

Stream and Streamer characteristics

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 cumulative (%) 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 cumulative (%) duration (min)

(b) Streamer

Duration of streams and aggregate duration of streamers

0.2 0.4 0.6 0.8 1 0 10 20 30 40 50 60 70 80 90 100 agregate views stream rank

(c) Stream

0.2 0.4 0.6 0.8 1 0 10 20 30 40 50 60 70 80 90 100 agregate views streamer rank

(d) Streamer

Stream and streamer audience 14 / 38 Watch me playing, I am a professional

slide-15
SLIDE 15

1 A first characterization of the E-Sport community 2 Predicting stream popularity 3 Ranking streamers 4 Conclusion and perspectives

slide-16
SLIDE 16

Predicting stream popularity

Motivation

Current Twitch recommendation strategy New and interesting streams may take too long (or even never) to become visible

16 / 38 Watch me playing, I am a professional

slide-17
SLIDE 17

Predicting stream popularity

Motivation

Streaming sessions have a highly skewed popularity distribution, short duration, and slow popularity evolution.

0.2 0.4 0.6 0.8 1 0 10 20 30 40 50 60 70 80 90 100 agregate views stream rank

(e)

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 cumulative (%) duration (min)

(f)

0.05 0.1 0.15 0.2 0.25 0.3 2 4 6 8 10 12 14 16 proportion of the overall maximal popularity hours since the beginning of a session average session for the top-100 streamers

(g)

Stream popularity, duration and popularity evolution 17 / 38 Watch me playing, I am a professional

slide-18
SLIDE 18

Predicting stream popularity

Idea

Predicting popularity using initial popularity records

100 101 102 103 104 105 100 101 102 103 104 105 popularity after 1 hour popularity after ti minutes

(h) ti = 5 min.

100 101 102 103 104 105 100 101 102 103 104 105 popularity after 1 hour popularity after ti minutes

(i) ti = 30 min.

Correlation between stream popularity after ti minutes and 1 hour 18 / 38 Watch me playing, I am a professional

slide-19
SLIDE 19

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 correlation mean squared error ti (min) corr. ε

19 / 38 Watch me playing, I am a professional

slide-20
SLIDE 20

Predicting stream popularity

Prediction Model

Model log(pop(tf )) = β0 + β1 log(pop(ti)) + ǫ Predicted vs. actual (based on popularity after ti minutes)

100 101 102 103 104 105 100 101 102 103 104 105 actual popularity after 1 hour predicted popularity after 1 hour

(j) ti = 5 min.

100 101 102 103 104 105 100 101 102 103 104 105 actual popularity after 1 hour predicted popularity after 1 hour

(k) ti = 30 min.

20 / 38 Watch me playing, I am a professional

slide-21
SLIDE 21

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 correlation mean squared error ti (min) corr. ε

21 / 38 Watch me playing, I am a professional

slide-22
SLIDE 22

1 A first characterization of the E-Sport community 2 Predicting stream popularity 3 Ranking streamers 4 Conclusion and perspectives

slide-23
SLIDE 23

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 / 38 Watch me playing, I am a professional

slide-24
SLIDE 24

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 are not comparable with Mill.Stephano.

crawl time

  • Oct. 29 16:30
  • Oct. 29 16:35
  • Nov. 10 19:00

EG.IdrA 1950 6350 1020 Mill.Stephano 4450 3680

  • WhiteRa

935 2301 4535

24 / 38 Watch me playing, I am a professional

slide-25
SLIDE 25

Ranking streamers

Challenge

Difficulty 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 voters and apply a Condorcet method that is known to be good for ranking: Maximum Majority Voting.

25 / 38 Watch me playing, I am a professional

slide-26
SLIDE 26

Ranking streamers

Ranking the pairs of streamers

Three criteria with the following precedence: c1 How often the first streamer is preferred to the second; c2 How often they have the exact same popularity; c3 How often they broadcast at the same time.

c1 c2 c3 (EG.IdrA,WhiteRa) 0.9615 156 (EG.IdrA,Mill.Stephano) 0.9 20 (WhiteRa,Mill.Stephano) 0.7829 175

26 / 38 Watch me playing, I am a professional

slide-27
SLIDE 27

Ranking streamers

Building an acyclic directed graph

Until all ranked pairs are processed:

1

Add all tied pairs as edges;

2

For every newly added edge, decide the existence of a cycle involving it;

3

Remove those involved in a cycle;

4

Go to 1.

27 / 38 Watch me playing, I am a professional

slide-28
SLIDE 28

Ranking streamers

Resulting graph

28 / 38 Watch me playing, I am a professional

slide-29
SLIDE 29

Ranking streamers

Results with Top-100 streamers

Focusing on eight StarCraft II players

Web poll (# votes) Simple ranking (pos.) Condorcet WhiteRa (11,112) EG.IdrA (20) EG.IdrA Mill.Stephano (9,192) WhiteRa (21) Mill.Stephano EG.IdrA (6,746) Liquid’Ret (31) EG.HuK EG.HuK (5,050) EG.HuK (32) WhiteRa Liquid‘HerO (2,160) Mill.Stephano (33) Liquid‘HerO Liquid’Sheth (846) Liquid‘HerO (53) QxG.SaSe QxG.SaSe (833) Liquid’Sheth (72) Liquid’Sheth Liquid’Ret (684) QxG.SaSe (91) Liquid’Ret

29 / 38 Watch me playing, I am a professional

slide-30
SLIDE 30

1 A first characterization of the E-Sport community 2 Predicting stream popularity 3 Ranking streamers 4 Conclusion and perspectives

slide-31
SLIDE 31

Conclusion and perspectives

Conclusion

Characterization of a new Web community

Gathered around social TV (Twitch.tv) Quantitative and qualitative characterization Popular tournaments and releases translate into audience Early prediction of future audience of a stream Ranking popular players via a Condorcet method

A particular interest

For the actors of this community (spectators, pro-gamers, sponsors, game publishers, etc.) For the research community (social network, data-mining, social sciences, etc.)

31 / 38 Watch me playing, I am a professional

slide-32
SLIDE 32

Conclusion and perspectives

Going further into the characterization

A community per se

accommodated with Web technologies, intensively using Web media like Facebook, Twitter, YouTube, and very active,

making it an interesting study case for researchers. Further work

A better characterization, including other media/data Formally define entities, relations, dimensions, etc

32 / 38 Watch me playing, I am a professional

slide-33
SLIDE 33

Conclusion and perspectives

Examples

Propagation

Data: Facebook and Twitter streaming announcements Question: How does it propagate into audience?

Network dynamics & Popularity

Data: List of IRC users logged in and watching a stream Question: are spectators structured into (evolving) sub-communities? Question: Can we translate spectator moving from a stream to another into popularity?

33 / 38 Watch me playing, I am a professional

slide-34
SLIDE 34

Conclusion and perspectives

Examples

Popularity: a point of view, depends on several factors

Data: Twitch audience, chat session (sentiment analysis) Data: Forum fan-club, e.g. TeamLiquid.net Data: Official season ranking Data: Records of ladder games, e.g. A won against B on day C Question: How/can “Skylines” determine best players? Question: Can we early predict rising/dying stars?

Personal recommendation

Data: Twitch data Question: How to recommend an interesting and unknown stream for a spectator?

34 / 38 Watch me playing, I am a professional

slide-35
SLIDE 35

Conclusion and perspectives

Examples

Facebook, tweets, IRC events, etc.

NLP, sentiment analysis (each game has a specific vocabulary) Graph-mining, network analysis

35 / 38 Watch me playing, I am a professional

slide-36
SLIDE 36

Conclusion and perspectives

Examples

Artificial Intelligence Abstracting (very!) noisy series of events, without knowing the game state that remains to be approximated

36 / 38 Watch me playing, I am a professional

slide-37
SLIDE 37

Conclusion and perspectives

Examples

37 / 38 Watch me playing, I am a professional

slide-38
SLIDE 38

Conclusion and perspectives

Thank you!

All datasets used for this article are available http://homepages.dcc.ufmg.br/~kaytoue/ Other datasets kaytoue@dcc.ufmg.br

38 / 38 Watch me playing, I am a professional