========================================================
                Supplemental Material to

     Toxicity Detection in Multiplayer Online Games

========================================================

Content
=======

1. Word annotations
1.1 non-latin
1.2 praise
1.3 bad
1.4 laughter
1.5 smiley
1.6 symbol
1.7 slang
1.8 command
1.9 stop
1.10 timemark

2. Toxic n-grams

----------------------------------------------------------
1. Word annotations
===================

1.1 non-latin
special characters, foreign language

pattern: includes a non ASCII-symbol



1.2 praise
acts of courtesy, kindness, sport spirit or gratitude

list: 
['gl','hf','glhf','gg','wp','thx','gj','nice','ty']



1.3 bad
profanity, swear words, inappropriate language

list: all words from (http://www.cs.cmu.edu/~biglou/resources/bad-words.txt)
letterset: ['noob','noobs','retard','retards','tard','tards','idiot','idiots','stupid','moron','morons','fu','nap']



1.4 laugther
acronyms expressing laughter

letterset: ['hahahaha','lol','rofl','lmao']



1.5 smiley
emoticon, symbols resembling faces or emotions

pattern: starts with either ':', ';' and is no longer than 6 characters
list: 
['=)','=))','=(','=D','=/','=\\','=)))','=?','=.=','=P','=))))','=]','=O','=)))))', 
'-.-', '-_-', "-.-'", '-,-', '-.-"', '-..-', "-_-'", '-.-*', '-__-',
'>.<', '>_>','>.>','>_<','>:D','<.<',
'^^','^_^','^^^','^.^', "^^'",'^-^','._.','TT','T_T','xd','XD','xD','oO','Oo','O_O','o_o','o_O','O_o']



1.6 symbol
symbols or numbers

pattern: either word is numeric OR word contains only non alphanumeric symbols



1.7 slang
DotA-specific game-technical terms, used to coordinate with team

list: 

a) Terms based on Dota 2 glossary (http://dota2.gamepedia.com/Glossary)
['bottle crow', 'ck', 'ss', 'cm', 'lothars or lothars edge', 'rat', 'safe lane', 'tp', 'gg', 'mid', 'squishy', 
'feeder', 'fade time', 'kotl', 'dot', 'fortification', 'ks', 'micro', 'bb', 'long lane', 'et', 'suicide lane', 
'ggwp', 'pl', 'jungling', 'qop', 'summoner', 'solo', 'aoe', 'ff', 'mkb', 'skill shot', 'ww', 'support', 'proc', 
'bd', 'potm', 'tb', 'ro3', 'pull or pulling', 'pet', 'sf', 'farm or farming', 'sb', 'cc', 'fog of war', 'wd', 
'deny', 'dp', 'cd', 'ricer', 'sk', 'aa', 'aggro|aggro', 'dd', 'debuff', 'observer ward|wards', 'hh', 'buildings#barracks|barracks', 
'flash farming', 'ulti', 'carry', 'caster', 'wr', 'bs', 'ac', 'cw', 'throne', 'wipe', 'miss or mia', 'nuke', 'silence', 
'ms', 'bot or bottom(btm)', 'es', 'roamer', 'sheepstick', 'wp', 'tank', 'fow', 'buff', 'pa', 'cooldown (cd)', 'hard carry', 
'cancer', 'jungler', 'necro', 'true sight', 'flash farming skill/ability', 'stacking', 'throw', 'offlane', 'am', 'furion', 
'glhf', 'hard lane', 'short lane', 'orb walk', 'reuse', 'cs', 'first blood|fb', 'recrow', 'easy lane', 'rax', 'kite or kiting', 
'oom', 'bkb', 'brb', 'roshan or rosh', 'ta', 'dps', 'b', 'disable', 'top', 'attack_speed#base_attack_time|bat', 'pp', 
'burst or burst damage', 'p', 'sny', 'chicken or chick', 'crow', 'rp', 'ganking|gank', 'bot, bots', 'exp', 'static farming']

b) Names of heroes
['admiral','alchemist','rexxar','bm','cent','es','omni','panda','sven','tiny','tc','tp','io',
'wisp','alch','clock','rattle','dk','huskar','bristle','bb','phoenix','tusk','tuskar',
'tres','tresdin','rizzrak','es','am','sniper','troll','jugg','juggernaut','luna','morph',
'morphling','meepo','naga','phantom','pl','potm','riki','rikimaru','gyro','drow','traxex',
'ta','lanaya','ursa','venge','vengeful','gondar','bh','xin','ember','cm','crystal','rylai',
'ench','enchantress','puck','chen','kotl','zeus','furi','furion','malfurion','silencer','nortrom',
'lina','slayer','storm','wind','wr','windrunner','disruptor','thrall','ogre','techies','jakiro',
'tinker','rasta','rhasta','rubick','rubik','sky','skywrath','oracle','axe','chaos','doom','naix','abaddon',
'abba','bane','lycan','night','azgalor','pit','pudge','sk','slardar','dirge','undying','tide','tidehunter',
'magnus','bara','spiritbreaker','sand','sand king','crixalis','blood','clinkz','brood','nyx','weaver',
'mort','pa','mortred','sf','shadow','shadow fiend','terror','terrorblade','spectre','mercurial','veno',
'venomancer','viper','razor','slark','void','faceless','medusa','dusa','zet','arc','arc warden','bane',
'dark','dp','death','lion','enigma','lich','necro','necrolyte','pugna','oblivion','desi','od','qop','warlock',
'shadow','sd','bat','batrider','dazzle','kael','invoker','invo','visage','lesh','leshrac','wd','witch doctor',
'aa','ww','winter','mirana','mira','trax','husk','legion','jugger','akasha','crix','kunka','kunkka','mother',
'nerub','rasta','maiden','shaker','balanar','dirge']

c) Names of items
['ac','heart','bkb','aegis','shiva','shivas','bloodstone','linken','linkens','van','vanguard','bm',
'blademail','blade','hood','manta','scythe','sheep','sheepstick','orchid','eul','euls','force','force staff',
'dagon','necro','necrobook','agh','aghs','aghanims','refresh','refresher','veil','rod','atos','mek','mekansm',
'vlad','vlads','boots','arcane','manaboots','aquila','buckler','branch','ring','basi','basil','basilius','pipe',
'urn','head','headress','medallion','drums','janggo','tranquil','tranquils','divine','rapier','mkb','radiance','radi',
'butterfly','buri','basher','battlefury','abyss','crystalys','crit','armlet','lothar','lothars','etheral','eblade',
'sange','yasha','satanic','mjollnir','skadi','helm','mael','maelstrom','deso','desolator','mom','diffusal','hh',
'halberd','bot','bots','phase','treads','soul','midas','perseverance','poorman','bracer','wraithband','null','wand',
'stick','gloves','mask','kelen','kelens','blink','sobi','boots','gem','cloak','evasion','ghost','shadow','clarity',
'salve','healing','tango','bottle','ward','obs','sentries','sentry','dust','smoke','chicken',
'bird','donkey','tp','flying','gauntlet','gauntlets','slippers','mantle','ironwood','belt','robe','circ','circlet',
'orb','claws','claymore','stout','shield','javelin','mithril','chain','helm','plate','quelling','blade','relic',
'void','venom','wards','dagger','courier','meka','agha','maelstorm']

d) game technical terms
['crow','cs','deny','dive','farm','gang','gank','push','juke','pull','juked',
'juking','pushed','woods','wood','jungle','lane','off','safe','quas','wex','exort',
'care','rosh','ult','ulti','missing','miss','bot','top','mid','help','stun','sup',
'support','carry','rune','haste','dd','invis','roam','creep','ancient','ancients',
'camp','block','disable','miss','report','tower','gg','wp','ez','back','bb','bbb','regen',
'fountain','base','gj','take','mana','oom','omw','back','stay','heal','hex','afk','creeps',
'farming','roshan','warded','cares','bottom','ulty','go','rax']



1.8 command
in-game commands, control words to trigger certain effects

pattern: word starts with either '!' or '-'



1.9 stop
English stop word

list: 
['a', 'an', 'another', 'any', 'certain', 'each', 'every', 'her', 'his', 'its', 'its', 'my', 
'no', 'our', 'some', 'that', 'the', 'their', 'this', 'and', 'but', 'or', 'yet', 'for', 'nor', 
'so', 'as', 'aboard', 'about', 'above', 'across', 'after', 'against', 'along', 'around', 'at', 
'before', 'behind', 'below', 'beneath', 'beside', 'between', 'beyond', 'but', 'by', 'down', 
'during', 'except', 'following', 'for', 'from', 'in', 'inside', 'into', 'like', 'minus', 
'minus', 'near', 'next', 'of', 'off', 'on', 'onto', 'onto', 'opposite', 'out', 'outside', 'over', 
'past', 'plus', 'round', 'since', 'since', 'than', 'through', 'to', 'toward', 'under', 
'underneath', 'unlike', 'until', 'up', 'upon', 'with', 'without', 'i','u','me','you','we','is',
'dont','all','y','can','it','get','have','why','need','he','come','just','not','are','they','now',
'got','ok','what','was','will','do','if']



1.10 timemark
automatically generated time-stamp, prepended in pause-mode

pattern: matches '[dd:dd]' where d is a digit {0123456789}



----------------------------------------------------------
2. Toxic n-grams
================

2.1 Toxic unigrams
'noob'
'idiot'
'fu'
'retard'
'noobs'
'tard'
'idiots'
'stupid'
'moron'
'retards'
'bitch'
'tards'
'nap'
'fucker'
'fucktard'
'nooob'
'motherfucker'
'morons'
'retarded'
'noob?'
'blind?'
'gay'
'blind'
'kid'
'asshole'
'pussy'
'sucker'
'fuckers'
'dumb'
'fag'
'idiot?'
'retard?'
'faggot'
'loser'
'nob'
'nooobs'
'bitches'
'noooob'
'dumbass'
'fuuu'
'fuu'
'stupid?'
'ass'
'stupids'
'cunt'



2.2 Toxic bigrams
('mother', 'fker')
('noob', 'shittttttttttttttt')
('fker', 'noob')
('kkkkkkkkkkkk??????????????', 'u')
('fucking', 'noob')
('fuck', 'u')
('u', 'suck')
('fuck', 'you')
('u', 'fucking')
('fucking', 'idiot')
('fuck', 'off')
('a', 'noob')
('fucking', 'retard')
('you', 'fucking')
('fucking', 'noobs')
('noob', 'team')
('you', 'suck')
('u', 'noob')
('suck', 'my')
('piece', 'of')
('fucking', 'tard')



2.3 Toxic trigrams
('mother', 'fker', 'noob')
('fker', 'noob', 'shittttttttttttttt')
('u', 'such', 'mother')
('such', 'mother', 'fker')
('piece', 'of', 'shit')
('suck', 'my', 'dick')
('what', 'a', 'noob')
('shut', 'the', 'fuck')
('u', 'are', 'noob')
('the', 'fuck', 'u')
('u', 'fucking', 'noob')
('son', 'of', 'a')
('fu', 'fu', 'fu')
('are', 'u', 'fucking')
('u', 'are', 'fucking')
('he', 'is', 'noob')
('are', 'you', 'fucking')
('die', 'in', 'hell')
('a', 'fucking', 'noob')
('u', 'suck', 'so')
('such', 'a', 'noob')
('you', 'are', 'noob')
('you', 'are', 'fucking')
('u', 'fucking', 'idiot')
('fucking', 'noob', 'team')
('go', 'fuck', 'yourself')
('so', 'fucking', 'bad')
('u', 'fucking', 'retard')
('fuck', 'your', 'mother')
('noob', 'noob', 'noob')
('you', 'suck', 'so')
('u', 'are', 'idiot')



2.4 Toxic quadgrams
('mother', 'fker', 'noob', 'shittttttttttttttt')
('u', 'such', 'mother', 'fker')
('such', 'mother', 'fker', 'noob')
('shut', 'the', 'fuck', 'up')
('son', 'of', 'a', 'bitch')
('why', 'the', 'fuck', 'u')
('fu', 'fu', 'fu', 'fu')
('the', 'fuck', 'are', 'you')
('u', 'suck', 'so', 'hard')
('of', 'shit', 'you', 'are')
('the', 'fuck', 'are', 'u')
('piece', 'of', 'shit', 'you')
('fucking', 'piece', 'of', 'shit')
('u', 'piece', 'of', 'shit')
('what', 'the', 'fuck', 'are')
('noob', 'noob', 'noob', 'noob')
('you', 'suck', 'so', 'hard')
('saying', 'piece', 'of', 'shit')
('the', 'fuck', 'did', 'u')
('u', 'are', 'fucking', 'noob')
('you', 'are', 'a', 'noob')
('get', 'the', 'fuck', 'out')
('you', 'are', 'fucking', 'noob')
('u', 'are', 'a', 'fucking')
('you', 'are', 'so', 'fucking')
('u', 'suck', 'so', 'much')
('you', 'piece', 'of', 'shit')
('u', 'cant', 'do', 'shit')
('u', 'are', 'a', 'noob')
('u', 'son', 'of', 'a')
('retarded', 'piece', 'of', 'shit')
('what', 'a', 'fucking', 'noob')
('of', 'bitch', 'son', 'of')
('i', 'hope', 'u', 'die')
('a', 'piece', 'of', 'shit')
('u', 'suck', 'like', 'hell')