SlideShare a Scribd company logo
Linguistic Analysis of Toxic Behavior 
in an Online Video Game 
Haewoon Kwak* Jeremy Blackburn+ 
*Qatar Computing Research Institute 
+Telefonica Research 
EGG (Exploration on Games and Gamers) workshop 
November 10th 2014
Cyberbullying 
is the use of information technology to 
repeatedly harm or harass other people in 
a deliberate manner 
http://en.wikipedia.org/wiki/Cyberbullying
4 
Easy solution: player reports 
Additional effort is required to check whether 
the report is true or not
5 
The LoL Tribunal (2011-2014)
6 
Experienced player casts a vote for 
pardon or punish 
As of March 2013, 
105M votes are casted
Decision (Punish or pardon) 
Agreement (Majority, SM, OM) 
Outcome (Win or lose) 
User reports 
Chat logs 
In-game performance 
per match (up to 5) 
7
8 
5 vs 5 team competition game
Nexus 
Nexus
Data collected from three servers 
EUW NA KR All 
Reported players 649,419 590,311 220,614 1,460,344 
Matches 2,841,906 2,107,522 1,066,618 6,016,046 
Player reports 5,559,968 3,441,557 1,893,433 10,898,958 
* KR Tribunal starts from November 2012, while other two Tribunals start from May 2011. 
10
Our previous work on this dataset 
• “STFU NOOB! Predicting crowdsourced decisions on 
toxic behavior in online games” (WWW’14) 
• “Exploring Cyberbullying and Other Toxic Behavior in 
Team Competition Online Games” (under review) 
11
Prevalent chat-related toxic behavior! 
12
http://elohell.net/chill/248678/chat-behaviour
• Explore the linguistic component of chat-related toxic 
behavior based on the large-scale Tribunal data 
14 
Research goal
15 
Begin with basic statistics
• 3.139 uni-grams (toxic players) vs. 2.732 uni-grams (typical 
players) are used per message. 
• However, typical players send 38% more messages than 
toxic players per game. 
16 
Longer messages of toxic players
Non-uniform communication during the match 
17
Three phases of the game: Early-mid-end game 
early mid end 
“gl hf” “gg” 
18
At some point, toxic-players begin to chat more 
19
20 
Do they use different words?
Top 1,000 uni- and bi-grams of typical and toxic players 
• 867 uni-grams and 748 bi-grams are common! 
• (1000-867) = 133 uni-grams and (1000-748) = 252 bi-grams 
are exclusively used by toxic players 
• We call them toxic uni- and bi-grams. 
• Then, what are toxic uni- and bi-grams? 
21
22 
Discriminative uni- and bi-grams
23 
Strategy vs. bad words
24 
Various emoticons
Some variations of the fxxx by toxic players 
(fxxx itself is also widely used by typical players) 
25
26 
When toxic bi-grams are 
frequently used?
Three different temporal patterns of bi-grams 
(based on when its peak comes) 
27 
early-bigrams mid-bigrams late-bigrams
80% of toxic bigrams are late-bigrams 
• Most of chat-related toxic playing occur at the late stage 
of the game! 
• Verbal abuse is most likely a response to losing a game 
• Through manual inspection of bi-grams containing ‘bot’, 
• early-bigrams is non-aggressive, 
• mid-bigrams are cursing, 
• and the late-bigrams are blaming. 
28
Different temporal patterns of common words 
• For toxic and typical players, we extract top 30 uni-grams 
at each time (0-100) 
• We get unique 80 uni-grams for toxic players and 91 uni-grams 
for typical players (top 30 uni-grams are stable) 
• We compute the normalized time of last use by toxic 
players and normal players, respectively. 
• Finally, we compute the difference of the last used time 
between toxic and normal players for common uni-grams. 
29
Differently used common uni-grams (△>30) 
30
31 
How to read the table? 
Toxic players stop actively using ‘gj’ at (T-31) 
but typical players still say it at T.
32 
Smile emoticons & apologies are (almost) 
never used by toxic players
But…appreciation is used by toxic players until 
some point 
33
Also, some words for strategic team maneuvers 
are the same 
34
Toxic players behave the same as normal 
players during the early stage of the match! 
• At some point they change their behavior like a phase 
transition 
• Utter neither apologies, praise, …etc. 
• Stop strategic communications 
✓We show not just how different toxic players are, but 
when they become different as well 
35
• Chat are not uniform during the match 
• Discriminative uni- and bi-grams used by typical and toxic 
players as signatures of them 
• Most of toxic bi-grams are found at the end of the game 
• Toxic players express their toxicity at some point, while 
they behave the same as typical players in early game 
• Implication: help to develop a pre-warning system to 
detect toxic playing 
36 
Summary - our findings

More Related Content

What's hot

Gamec Theory
Gamec TheoryGamec Theory
Advanced Game Theory guest lecture
Advanced Game Theory guest lectureAdvanced Game Theory guest lecture
Advanced Game Theory guest lecture
Jonas Heide Smith
 
Ssrn a brief inrtoduction to the basic of game theory
Ssrn a brief inrtoduction to the basic of game theorySsrn a brief inrtoduction to the basic of game theory
Ssrn a brief inrtoduction to the basic of game theory
Ying wei (Joe) Chou
 
GT Presentation
GT PresentationGT Presentation
GT Presentation
Arif Hussain
 
History through video games
History through video games History through video games
History through video games
Darren Terry
 
StatsSuperbowlprediction
StatsSuperbowlpredictionStatsSuperbowlprediction
StatsSuperbowlprediction
yuan gao
 
Game Theory
Game TheoryGame Theory
Game Theory
Ali Salek
 

What's hot (7)

Gamec Theory
Gamec TheoryGamec Theory
Gamec Theory
 
Advanced Game Theory guest lecture
Advanced Game Theory guest lectureAdvanced Game Theory guest lecture
Advanced Game Theory guest lecture
 
Ssrn a brief inrtoduction to the basic of game theory
Ssrn a brief inrtoduction to the basic of game theorySsrn a brief inrtoduction to the basic of game theory
Ssrn a brief inrtoduction to the basic of game theory
 
GT Presentation
GT PresentationGT Presentation
GT Presentation
 
History through video games
History through video games History through video games
History through video games
 
StatsSuperbowlprediction
StatsSuperbowlpredictionStatsSuperbowlprediction
StatsSuperbowlprediction
 
Game Theory
Game TheoryGame Theory
Game Theory
 

Similar to Linguistic Analysis of Toxic Behavior in an Online Video Game

Coping with Verbal Abuse in Online Games
Coping with Verbal Abuse in Online GamesCoping with Verbal Abuse in Online Games
Coping with Verbal Abuse in Online Games
Denique Ferguson
 
Counter-Strike: Viewing Guide for the ELEAGUE Major
Counter-Strike: Viewing Guide for the ELEAGUE MajorCounter-Strike: Viewing Guide for the ELEAGUE Major
Counter-Strike: Viewing Guide for the ELEAGUE Major
Luc Ryu, CPA, CA, CBV
 
LAFS Game Design 1 - Structural Elements
LAFS Game Design 1 - Structural ElementsLAFS Game Design 1 - Structural Elements
LAFS Game Design 1 - Structural Elements
David Mullich
 
Game theory
Game theoryGame theory
Game theory
Soumya Bilwar
 
Game Theory Economics
Game Theory EconomicsGame Theory Economics
Analysis on steam platform
Analysis on steam platformAnalysis on steam platform
Analysis on steam platform
Yousef Fadila
 

Similar to Linguistic Analysis of Toxic Behavior in an Online Video Game (6)

Coping with Verbal Abuse in Online Games
Coping with Verbal Abuse in Online GamesCoping with Verbal Abuse in Online Games
Coping with Verbal Abuse in Online Games
 
Counter-Strike: Viewing Guide for the ELEAGUE Major
Counter-Strike: Viewing Guide for the ELEAGUE MajorCounter-Strike: Viewing Guide for the ELEAGUE Major
Counter-Strike: Viewing Guide for the ELEAGUE Major
 
LAFS Game Design 1 - Structural Elements
LAFS Game Design 1 - Structural ElementsLAFS Game Design 1 - Structural Elements
LAFS Game Design 1 - Structural Elements
 
Game theory
Game theoryGame theory
Game theory
 
Game Theory Economics
Game Theory EconomicsGame Theory Economics
Game Theory Economics
 
Analysis on steam platform
Analysis on steam platformAnalysis on steam platform
Analysis on steam platform
 

More from Haewoon Kwak

Multiplex Media Attention and Disregard Network among 129 Countries
Multiplex Media Attention and Disregard Network among 129 CountriesMultiplex Media Attention and Disregard Network among 129 Countries
Multiplex Media Attention and Disregard Network among 129 Countries
Haewoon Kwak
 
Revealing the Hidden Patterns of News Photos: Analysis of Millions of News Ph...
Revealing the Hidden Patterns of News Photos: Analysis of Millions of News Ph...Revealing the Hidden Patterns of News Photos: Analysis of Millions of News Ph...
Revealing the Hidden Patterns of News Photos: Analysis of Millions of News Ph...
Haewoon Kwak
 
Multi-level analysis on structures and dynamics of OSN
Multi-level analysis on structures and dynamics of OSNMulti-level analysis on structures and dynamics of OSN
Multi-level analysis on structures and dynamics of OSN
Haewoon Kwak
 
Exploring cyberbullying and 
other toxic behavior in 
team competition online...
Exploring cyberbullying and 
other toxic behavior in 
team competition online...Exploring cyberbullying and 
other toxic behavior in 
team competition online...
Exploring cyberbullying and 
other toxic behavior in 
team competition online...
Haewoon Kwak
 
Fragile Online Relationship: A First Look at Unfollow Dynamics in Twitter
Fragile Online Relationship: A First Look at Unfollow Dynamics in TwitterFragile Online Relationship: A First Look at Unfollow Dynamics in Twitter
Fragile Online Relationship: A First Look at Unfollow Dynamics in Twitter
Haewoon Kwak
 
Comparison of Online Social Relations in terms of Volume vs. Interaction: A C...
Comparison of Online Social Relations in terms of Volume vs. Interaction: A C...Comparison of Online Social Relations in terms of Volume vs. Interaction: A C...
Comparison of Online Social Relations in terms of Volume vs. Interaction: A C...
Haewoon Kwak
 
What is Twitter, a Social Network or a News Media?
What is Twitter, a Social Network or a News Media? What is Twitter, a Social Network or a News Media?
What is Twitter, a Social Network or a News Media?
Haewoon Kwak
 
Mining Communities in Networks: A Solution for Consistency and Its Evaluation
Mining Communities in Networks: A Solution for Consistency and Its EvaluationMining Communities in Networks: A Solution for Consistency and Its Evaluation
Mining Communities in Networks: A Solution for Consistency and Its Evaluation
Haewoon Kwak
 

More from Haewoon Kwak (8)

Multiplex Media Attention and Disregard Network among 129 Countries
Multiplex Media Attention and Disregard Network among 129 CountriesMultiplex Media Attention and Disregard Network among 129 Countries
Multiplex Media Attention and Disregard Network among 129 Countries
 
Revealing the Hidden Patterns of News Photos: Analysis of Millions of News Ph...
Revealing the Hidden Patterns of News Photos: Analysis of Millions of News Ph...Revealing the Hidden Patterns of News Photos: Analysis of Millions of News Ph...
Revealing the Hidden Patterns of News Photos: Analysis of Millions of News Ph...
 
Multi-level analysis on structures and dynamics of OSN
Multi-level analysis on structures and dynamics of OSNMulti-level analysis on structures and dynamics of OSN
Multi-level analysis on structures and dynamics of OSN
 
Exploring cyberbullying and 
other toxic behavior in 
team competition online...
Exploring cyberbullying and 
other toxic behavior in 
team competition online...Exploring cyberbullying and 
other toxic behavior in 
team competition online...
Exploring cyberbullying and 
other toxic behavior in 
team competition online...
 
Fragile Online Relationship: A First Look at Unfollow Dynamics in Twitter
Fragile Online Relationship: A First Look at Unfollow Dynamics in TwitterFragile Online Relationship: A First Look at Unfollow Dynamics in Twitter
Fragile Online Relationship: A First Look at Unfollow Dynamics in Twitter
 
Comparison of Online Social Relations in terms of Volume vs. Interaction: A C...
Comparison of Online Social Relations in terms of Volume vs. Interaction: A C...Comparison of Online Social Relations in terms of Volume vs. Interaction: A C...
Comparison of Online Social Relations in terms of Volume vs. Interaction: A C...
 
What is Twitter, a Social Network or a News Media?
What is Twitter, a Social Network or a News Media? What is Twitter, a Social Network or a News Media?
What is Twitter, a Social Network or a News Media?
 
Mining Communities in Networks: A Solution for Consistency and Its Evaluation
Mining Communities in Networks: A Solution for Consistency and Its EvaluationMining Communities in Networks: A Solution for Consistency and Its Evaluation
Mining Communities in Networks: A Solution for Consistency and Its Evaluation
 

Recently uploaded

DIGIDEVTV A New area of OTT Distribution
DIGIDEVTV  A New area of OTT DistributionDIGIDEVTV  A New area of OTT Distribution
DIGIDEVTV A New area of OTT Distribution
joeqsm
 
Modern Radio Frequency Access Control Systems: The Key to Efficiency and Safety
Modern Radio Frequency Access Control Systems: The Key to Efficiency and SafetyModern Radio Frequency Access Control Systems: The Key to Efficiency and Safety
Modern Radio Frequency Access Control Systems: The Key to Efficiency and Safety
AITIX LLC
 
Christian Louboutin: Innovating with Red Soles
Christian Louboutin: Innovating with Red SolesChristian Louboutin: Innovating with Red Soles
Christian Louboutin: Innovating with Red Soles
get joys
 
From Teacher to OnlyFans: Brianna Coppage's Story at 28
From Teacher to OnlyFans: Brianna Coppage's Story at 28From Teacher to OnlyFans: Brianna Coppage's Story at 28
From Teacher to OnlyFans: Brianna Coppage's Story at 28
get joys
 
The Unbelievable Tale of Dwayne Johnson Kidnapping: A Riveting Saga
The Unbelievable Tale of Dwayne Johnson Kidnapping: A Riveting SagaThe Unbelievable Tale of Dwayne Johnson Kidnapping: A Riveting Saga
The Unbelievable Tale of Dwayne Johnson Kidnapping: A Riveting Saga
greendigital
 
Snoopy boards the big bow wow musical __
Snoopy boards the big bow wow musical __Snoopy boards the big bow wow musical __
Snoopy boards the big bow wow musical __
catcabrera
 
University of Western Sydney degree offer diploma Transcript
University of Western Sydney degree offer diploma TranscriptUniversity of Western Sydney degree offer diploma Transcript
University of Western Sydney degree offer diploma Transcript
soxrziqu
 
The Gallery of Shadows, In the heart of a bustling city
The Gallery of Shadows, In the heart of a bustling cityThe Gallery of Shadows, In the heart of a bustling city
The Gallery of Shadows, In the heart of a bustling city
John Emmett
 
Everything You Need to Know About IPTV Ireland.pdf
Everything You Need to Know About IPTV Ireland.pdfEverything You Need to Know About IPTV Ireland.pdf
Everything You Need to Know About IPTV Ireland.pdf
Xtreame HDTV
 
原版制作(Mercer毕业证书)摩斯大学毕业证在读证明一模一样
原版制作(Mercer毕业证书)摩斯大学毕业证在读证明一模一样原版制作(Mercer毕业证书)摩斯大学毕业证在读证明一模一样
原版制作(Mercer毕业证书)摩斯大学毕业证在读证明一模一样
mul1kv5w
 
Authenticity in Motion Pictures: How Steve Greisen Retains Real Stories
Authenticity in Motion Pictures: How Steve Greisen Retains Real StoriesAuthenticity in Motion Pictures: How Steve Greisen Retains Real Stories
Authenticity in Motion Pictures: How Steve Greisen Retains Real Stories
Steve Greisen
 
Unveiling Paul Haggis Shaping Cinema Through Diversity. .pdf
Unveiling Paul Haggis Shaping Cinema Through Diversity. .pdfUnveiling Paul Haggis Shaping Cinema Through Diversity. .pdf
Unveiling Paul Haggis Shaping Cinema Through Diversity. .pdf
kenid14983
 
Leonardo DiCaprio House: A Journey Through His Extravagant Real Estate Portfolio
Leonardo DiCaprio House: A Journey Through His Extravagant Real Estate PortfolioLeonardo DiCaprio House: A Journey Through His Extravagant Real Estate Portfolio
Leonardo DiCaprio House: A Journey Through His Extravagant Real Estate Portfolio
greendigital
 
定制(uow毕业证书)卧龙岗大学毕业证文凭学位证书原版一模一样
定制(uow毕业证书)卧龙岗大学毕业证文凭学位证书原版一模一样定制(uow毕业证书)卧龙岗大学毕业证文凭学位证书原版一模一样
定制(uow毕业证书)卧龙岗大学毕业证文凭学位证书原版一模一样
0md20cgg
 
Top IPTV UK Providers of A Comprehensive Review.pdf
Top IPTV UK Providers of A Comprehensive Review.pdfTop IPTV UK Providers of A Comprehensive Review.pdf
Top IPTV UK Providers of A Comprehensive Review.pdf
Xtreame HDTV
 
The Enigmatic Portrait, In the heart of a sleepy town
The Enigmatic Portrait, In the heart of a sleepy townThe Enigmatic Portrait, In the heart of a sleepy town
The Enigmatic Portrait, In the heart of a sleepy town
John Emmett
 
哪里买(osu毕业证书)美国俄勒冈州立大学毕业证双学位证书原版一模一样
哪里买(osu毕业证书)美国俄勒冈州立大学毕业证双学位证书原版一模一样哪里买(osu毕业证书)美国俄勒冈州立大学毕业证双学位证书原版一模一样
哪里买(osu毕业证书)美国俄勒冈州立大学毕业证双学位证书原版一模一样
9u08k0x
 
Emcee Profile_ Subbu from Bangalore .pdf
Emcee Profile_ Subbu from Bangalore .pdfEmcee Profile_ Subbu from Bangalore .pdf
Emcee Profile_ Subbu from Bangalore .pdf
subran
 
From Swing Music to Big Band Fame_ 5 Iconic Artists.pptx
From Swing Music to Big Band Fame_ 5 Iconic Artists.pptxFrom Swing Music to Big Band Fame_ 5 Iconic Artists.pptx
From Swing Music to Big Band Fame_ 5 Iconic Artists.pptx
Swing Street Radio
 
Orpah Winfrey Dwayne Johnson: Titans of Influence and Inspiration
Orpah Winfrey Dwayne Johnson: Titans of Influence and InspirationOrpah Winfrey Dwayne Johnson: Titans of Influence and Inspiration
Orpah Winfrey Dwayne Johnson: Titans of Influence and Inspiration
greendigital
 

Recently uploaded (20)

DIGIDEVTV A New area of OTT Distribution
DIGIDEVTV  A New area of OTT DistributionDIGIDEVTV  A New area of OTT Distribution
DIGIDEVTV A New area of OTT Distribution
 
Modern Radio Frequency Access Control Systems: The Key to Efficiency and Safety
Modern Radio Frequency Access Control Systems: The Key to Efficiency and SafetyModern Radio Frequency Access Control Systems: The Key to Efficiency and Safety
Modern Radio Frequency Access Control Systems: The Key to Efficiency and Safety
 
Christian Louboutin: Innovating with Red Soles
Christian Louboutin: Innovating with Red SolesChristian Louboutin: Innovating with Red Soles
Christian Louboutin: Innovating with Red Soles
 
From Teacher to OnlyFans: Brianna Coppage's Story at 28
From Teacher to OnlyFans: Brianna Coppage's Story at 28From Teacher to OnlyFans: Brianna Coppage's Story at 28
From Teacher to OnlyFans: Brianna Coppage's Story at 28
 
The Unbelievable Tale of Dwayne Johnson Kidnapping: A Riveting Saga
The Unbelievable Tale of Dwayne Johnson Kidnapping: A Riveting SagaThe Unbelievable Tale of Dwayne Johnson Kidnapping: A Riveting Saga
The Unbelievable Tale of Dwayne Johnson Kidnapping: A Riveting Saga
 
Snoopy boards the big bow wow musical __
Snoopy boards the big bow wow musical __Snoopy boards the big bow wow musical __
Snoopy boards the big bow wow musical __
 
University of Western Sydney degree offer diploma Transcript
University of Western Sydney degree offer diploma TranscriptUniversity of Western Sydney degree offer diploma Transcript
University of Western Sydney degree offer diploma Transcript
 
The Gallery of Shadows, In the heart of a bustling city
The Gallery of Shadows, In the heart of a bustling cityThe Gallery of Shadows, In the heart of a bustling city
The Gallery of Shadows, In the heart of a bustling city
 
Everything You Need to Know About IPTV Ireland.pdf
Everything You Need to Know About IPTV Ireland.pdfEverything You Need to Know About IPTV Ireland.pdf
Everything You Need to Know About IPTV Ireland.pdf
 
原版制作(Mercer毕业证书)摩斯大学毕业证在读证明一模一样
原版制作(Mercer毕业证书)摩斯大学毕业证在读证明一模一样原版制作(Mercer毕业证书)摩斯大学毕业证在读证明一模一样
原版制作(Mercer毕业证书)摩斯大学毕业证在读证明一模一样
 
Authenticity in Motion Pictures: How Steve Greisen Retains Real Stories
Authenticity in Motion Pictures: How Steve Greisen Retains Real StoriesAuthenticity in Motion Pictures: How Steve Greisen Retains Real Stories
Authenticity in Motion Pictures: How Steve Greisen Retains Real Stories
 
Unveiling Paul Haggis Shaping Cinema Through Diversity. .pdf
Unveiling Paul Haggis Shaping Cinema Through Diversity. .pdfUnveiling Paul Haggis Shaping Cinema Through Diversity. .pdf
Unveiling Paul Haggis Shaping Cinema Through Diversity. .pdf
 
Leonardo DiCaprio House: A Journey Through His Extravagant Real Estate Portfolio
Leonardo DiCaprio House: A Journey Through His Extravagant Real Estate PortfolioLeonardo DiCaprio House: A Journey Through His Extravagant Real Estate Portfolio
Leonardo DiCaprio House: A Journey Through His Extravagant Real Estate Portfolio
 
定制(uow毕业证书)卧龙岗大学毕业证文凭学位证书原版一模一样
定制(uow毕业证书)卧龙岗大学毕业证文凭学位证书原版一模一样定制(uow毕业证书)卧龙岗大学毕业证文凭学位证书原版一模一样
定制(uow毕业证书)卧龙岗大学毕业证文凭学位证书原版一模一样
 
Top IPTV UK Providers of A Comprehensive Review.pdf
Top IPTV UK Providers of A Comprehensive Review.pdfTop IPTV UK Providers of A Comprehensive Review.pdf
Top IPTV UK Providers of A Comprehensive Review.pdf
 
The Enigmatic Portrait, In the heart of a sleepy town
The Enigmatic Portrait, In the heart of a sleepy townThe Enigmatic Portrait, In the heart of a sleepy town
The Enigmatic Portrait, In the heart of a sleepy town
 
哪里买(osu毕业证书)美国俄勒冈州立大学毕业证双学位证书原版一模一样
哪里买(osu毕业证书)美国俄勒冈州立大学毕业证双学位证书原版一模一样哪里买(osu毕业证书)美国俄勒冈州立大学毕业证双学位证书原版一模一样
哪里买(osu毕业证书)美国俄勒冈州立大学毕业证双学位证书原版一模一样
 
Emcee Profile_ Subbu from Bangalore .pdf
Emcee Profile_ Subbu from Bangalore .pdfEmcee Profile_ Subbu from Bangalore .pdf
Emcee Profile_ Subbu from Bangalore .pdf
 
From Swing Music to Big Band Fame_ 5 Iconic Artists.pptx
From Swing Music to Big Band Fame_ 5 Iconic Artists.pptxFrom Swing Music to Big Band Fame_ 5 Iconic Artists.pptx
From Swing Music to Big Band Fame_ 5 Iconic Artists.pptx
 
Orpah Winfrey Dwayne Johnson: Titans of Influence and Inspiration
Orpah Winfrey Dwayne Johnson: Titans of Influence and InspirationOrpah Winfrey Dwayne Johnson: Titans of Influence and Inspiration
Orpah Winfrey Dwayne Johnson: Titans of Influence and Inspiration
 

Linguistic Analysis of Toxic Behavior in an Online Video Game

  • 1. Linguistic Analysis of Toxic Behavior in an Online Video Game Haewoon Kwak* Jeremy Blackburn+ *Qatar Computing Research Institute +Telefonica Research EGG (Exploration on Games and Gamers) workshop November 10th 2014
  • 2. Cyberbullying is the use of information technology to repeatedly harm or harass other people in a deliberate manner http://en.wikipedia.org/wiki/Cyberbullying
  • 3.
  • 4. 4 Easy solution: player reports Additional effort is required to check whether the report is true or not
  • 5. 5 The LoL Tribunal (2011-2014)
  • 6. 6 Experienced player casts a vote for pardon or punish As of March 2013, 105M votes are casted
  • 7. Decision (Punish or pardon) Agreement (Majority, SM, OM) Outcome (Win or lose) User reports Chat logs In-game performance per match (up to 5) 7
  • 8. 8 5 vs 5 team competition game
  • 10. Data collected from three servers EUW NA KR All Reported players 649,419 590,311 220,614 1,460,344 Matches 2,841,906 2,107,522 1,066,618 6,016,046 Player reports 5,559,968 3,441,557 1,893,433 10,898,958 * KR Tribunal starts from November 2012, while other two Tribunals start from May 2011. 10
  • 11. Our previous work on this dataset • “STFU NOOB! Predicting crowdsourced decisions on toxic behavior in online games” (WWW’14) • “Exploring Cyberbullying and Other Toxic Behavior in Team Competition Online Games” (under review) 11
  • 14. • Explore the linguistic component of chat-related toxic behavior based on the large-scale Tribunal data 14 Research goal
  • 15. 15 Begin with basic statistics
  • 16. • 3.139 uni-grams (toxic players) vs. 2.732 uni-grams (typical players) are used per message. • However, typical players send 38% more messages than toxic players per game. 16 Longer messages of toxic players
  • 18. Three phases of the game: Early-mid-end game early mid end “gl hf” “gg” 18
  • 19. At some point, toxic-players begin to chat more 19
  • 20. 20 Do they use different words?
  • 21. Top 1,000 uni- and bi-grams of typical and toxic players • 867 uni-grams and 748 bi-grams are common! • (1000-867) = 133 uni-grams and (1000-748) = 252 bi-grams are exclusively used by toxic players • We call them toxic uni- and bi-grams. • Then, what are toxic uni- and bi-grams? 21
  • 22. 22 Discriminative uni- and bi-grams
  • 23. 23 Strategy vs. bad words
  • 25. Some variations of the fxxx by toxic players (fxxx itself is also widely used by typical players) 25
  • 26. 26 When toxic bi-grams are frequently used?
  • 27. Three different temporal patterns of bi-grams (based on when its peak comes) 27 early-bigrams mid-bigrams late-bigrams
  • 28. 80% of toxic bigrams are late-bigrams • Most of chat-related toxic playing occur at the late stage of the game! • Verbal abuse is most likely a response to losing a game • Through manual inspection of bi-grams containing ‘bot’, • early-bigrams is non-aggressive, • mid-bigrams are cursing, • and the late-bigrams are blaming. 28
  • 29. Different temporal patterns of common words • For toxic and typical players, we extract top 30 uni-grams at each time (0-100) • We get unique 80 uni-grams for toxic players and 91 uni-grams for typical players (top 30 uni-grams are stable) • We compute the normalized time of last use by toxic players and normal players, respectively. • Finally, we compute the difference of the last used time between toxic and normal players for common uni-grams. 29
  • 30. Differently used common uni-grams (△>30) 30
  • 31. 31 How to read the table? Toxic players stop actively using ‘gj’ at (T-31) but typical players still say it at T.
  • 32. 32 Smile emoticons & apologies are (almost) never used by toxic players
  • 33. But…appreciation is used by toxic players until some point 33
  • 34. Also, some words for strategic team maneuvers are the same 34
  • 35. Toxic players behave the same as normal players during the early stage of the match! • At some point they change their behavior like a phase transition • Utter neither apologies, praise, …etc. • Stop strategic communications ✓We show not just how different toxic players are, but when they become different as well 35
  • 36. • Chat are not uniform during the match • Discriminative uni- and bi-grams used by typical and toxic players as signatures of them • Most of toxic bi-grams are found at the end of the game • Toxic players express their toxicity at some point, while they behave the same as typical players in early game • Implication: help to develop a pre-warning system to detect toxic playing 36 Summary - our findings