"You Know What to Do"

Video sharing platforms like YouTube are increasingly targeted by aggression and hate attacks. Prior work has shown how these attacks often take place as a result of "raids," i.e., organized efforts by ad-hoc mobs coordinating from third-party communities. Despite the increasing relevance of this phenomenon, however, online services often lack effective countermeasures to mitigate it. Unlike well-studied problems like spam and phishing, coordinated aggressive behavior both targets and is perpetrated by humans, making defense mechanisms that look for automated activity unsuitable. Therefore, the de-facto solution is to reactively rely on user reports and human moderation. In this paper, we propose an automated solution to identify YouTube videos that are likely to be targeted by coordinated harassers from fringe communities like 4chan. First, we characterize and model YouTube videos along several axes (metadata, audio transcripts, thumbnails) based on a ground truth dataset of videos that were targeted by raids. Then, we use an ensemble of classifiers to determine the likelihood that a video will be raided with very good results (AUC up to 94%). Overall, our work provides an important first step towards deploying proactive systems to detect and mitigate coordinated hate attacks on platforms like YouTube.

[1]  Gianluca Stringhini,et al.  POISED: Spotting Twitter Spam Off the Beaten Paths , 2017, CCS.

[2]  Senén Barro,et al.  Do we need hundreds of classifiers to solve real world classification problems? , 2014, J. Mach. Learn. Res..

[3]  Pete Burnap,et al.  Us and them: identifying cyber hate on Twitter across multiple protected characteristics , 2016, EPJ Data Science.

[4]  S. Chess,et al.  A Conspiracy of Fishes, or, How We Learned to Stop Worrying About #GamerGate and Embrace Hegemonic Masculinity , 2015 .

[5]  Ashish Sureka,et al.  Mining YouTube metadata for detecting privacy invading harassment and misdemeanor videos , 2014, 2014 Twelfth Annual International Conference on Privacy, Security and Trust.

[6]  WangGang,et al.  A comparative assessment of ensemble learning for credit scoring , 2011 .

[7]  Vivek K. Singh,et al.  See No Evil, Hear No Evil , 2018, Proc. ACM Hum. Comput. Interact..

[8]  Joel R. Tetreault,et al.  Abusive Language Detection in Online User Content , 2016, WWW.

[9]  Gianluca Stringhini,et al.  Detecting spammers on social networks , 2010, ACSAC '10.

[10]  P. Räsänen,et al.  Pro-Anorexia and Anti-Pro-Anorexia Videos on YouTube: Sentiment Analysis of User Responses , 2015, Journal of medical Internet research.

[11]  Thomas G. Dietterich Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[12]  Mai ElSherief,et al.  Hate Lingo: A Target-based Linguistic Analysis of Hate Speech in Social Media , 2018, ICWSM.

[13]  Jacob Eisenstein,et al.  You Can't Stay Here , 2017, Proc. ACM Hum. Comput. Interact..

[14]  Dolf Trieschnigg,et al.  Experts and Machines against Bullies: A Hybrid Approach to Detect Cyberbullies , 2014, Canadian Conference on AI.

[15]  Daniel Balcells Eichenberger Speech activity detection: Application-specific tuning and context-based neural approaches , 2016 .

[16]  Virgílio A. F. Almeida,et al.  Detecting Spammers and Content Promoters in Online Video Social Networks , 2009, IEEE INFOCOM Workshops 2009.

[17]  Gavin Brown,et al.  Ensemble Learning , 2010, Encyclopedia of Machine Learning and Data Mining.

[18]  Ria Verleur,et al.  Flaming on YouTube , 2010, Comput. Hum. Behav..

[19]  Justine Zhang,et al.  Characterizing Online Public Discussions through Patterns of Participant Interactions , 2018, Proc. ACM Hum. Comput. Interact..

[20]  Shivraj Sunil Marathe,et al.  Approaches for Mining YouTube Videos Metadata in Cyber bullying Detection , 2015 .

[21]  Kush R. Varshney,et al.  The Effect of Extremist Violence on Hateful Speech Online , 2018, ICWSM.

[22]  Gianluca Stringhini,et al.  Hate is not Binary: Studying Abusive Behavior of #GamerGate on Twitter , 2017, HT.

[23]  Dumitru Erhan,et al.  Show and Tell: Lessons Learned from the 2015 MSCOCO Image Captioning Challenge , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Gianluca Stringhini,et al.  EVILCOHORT: Detecting Communities of Malicious Accounts on Online Services , 2015, USENIX Security Symposium.

[25]  Daniele Quercia,et al.  The Social World of Content Abusers in Community Question Answering , 2015, WWW.

[26]  D. Green,et al.  Studying Hate Crime with the Internet: What Makes Racists Advocate Racial Violence? , 2002 .

[27]  Virgílio A. F. Almeida,et al.  Detecting Spammers on Twitter , 2010 .

[28]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Fei-Fei Li,et al.  Deep visual-semantic alignments for generating image descriptions , 2015, CVPR.

[30]  Jure Leskovec,et al.  Community Interaction and Conflict on the Web , 2018, WWW.

[31]  Gianluca Stringhini,et al.  Kek, Cucks, and God Emperor Trump: A Measurement Study of 4chan's Politically Incorrect Forum and Its Effects on the Web , 2016, ICWSM.

[32]  Srayan Datta,et al.  Identifying Misaligned Inter-Group Links and Communities , 2017, Proc. ACM Hum. Comput. Interact..

[33]  David H. Wolpert,et al.  Stacked generalization , 1992, Neural Networks.

[34]  Christian Rossow,et al.  Amplification Hell: Revisiting Network Protocols for DDoS Abuse , 2014, NDSS.

[35]  Daniel Povey,et al.  The Kaldi Speech Recognition Toolkit , 2011 .

[36]  Nikunj C. Oza,et al.  Online Ensemble Learning , 2000, AAAI/IAAI.

[37]  D. Grigg Cyber-Aggression: Definition and Concept of Cyberbullying , 2010, Australian Journal of Guidance and Counselling.

[38]  Zahra Ashktorab,et al.  Identifying Women's Experiences With and Strategies for Mitigating Negative Effects of Online Harassment , 2017, CSCW.

[39]  Ariadna Matamoros Fernández,et al.  Hate Speech and Covert Discrimination on Social Media: Monitoring the Facebook Pages of Extreme-Right Political Parties in Spain , 2016 .

[40]  A. Bruckman,et al.  Online Harassment and Content Moderation , 2018 .

[41]  Ashish Sureka,et al.  A focused crawler for mining hate and extremism promoting videos on YouTube. , 2014, HT.

[42]  Catherine Havasi,et al.  ConceptNet 5.5: An Open Multilingual Graph of General Knowledge , 2016, AAAI.

[43]  Krishna P. Gummadi,et al.  Towards Detecting Anomalous User Behavior in Online Social Networks , 2014, USENIX Security Symposium.

[44]  John J. Godfrey,et al.  SWITCHBOARD: telephone speech corpus for research and development , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[45]  Michael Green,et al.  The lesbian, gay, bisexual and transgender community online: discussions of bullying and self-disclosure in YouTube videos , 2015, Behav. Inf. Technol..

[46]  Siddhartha Bhattacharyya,et al.  Data mining for credit card fraud: A comparative study , 2011, Decis. Support Syst..

[47]  Vaibhava Goel,et al.  Segmental minimum Bayes-risk decoding for automatic speech recognition , 2004, IEEE Transactions on Speech and Audio Processing.

[48]  Ponnurangam Kumaraguru,et al.  Mining YouTube to Discover Extremist Videos, Users and Hidden Communities , 2010, AIRS.

[49]  Jacob Eisenstein,et al.  You Can't Stay Here , 2017 .

[50]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[51]  El-Sayed M. El-Alfy,et al.  Using Word Embedding and Ensemble Learning for Highly Imbalanced Data Sentiment Analysis in Short Arabic Text , 2017, ANT/SEIT.

[52]  Qiang Cao,et al.  Uncovering Large Groups of Active Malicious Accounts in Online Social Networks , 2014, CCS.

[53]  Maura Conway,et al.  Jihadi Video and Auto-radicalisation: Evidence from an Exploratory YouTube Study , 2008, EuroISI.

[54]  Mattias Ekman The dark side of online activism : Swedish right-wing extremist video activism on YouTube , 2014 .

[55]  Aishik Chakraborty,et al.  Conflicts : An Effective Route to Detect Incivility in Twitter 117 : 3 cell phones , and other electronic devices , 2018 .

[56]  A. Weaver,et al.  The (Non)Violent World of Youtube: Content Trends in Web Video (Top 3 Faculty Paper) , 2012 .

[57]  P. Sobkowicz,et al.  Dynamics of hate based Internet user networks , 2010 .

[58]  Sheena Erete,et al.  Snitches, Trolls, and Social Norms: Unpacking Perceptions of Social Media Use for Crime Prevention , 2017, CSCW.

[59]  K. Hazel Kwon,et al.  Is Aggression Contagious Online? A Case of Swearing on Donald Trump's Campaign Videos on YouTube , 2017, HICSS.

[60]  L. Jönson Flaming motivation in YouTube users as a function of the traits Disinhibition seeking, Assertiveness and Anxiety? , 2013 .

[61]  Paolo Gerbaudo,et al.  Social media and populism: an elective affinity? , 2018 .

[62]  Phyllis B. Gerstenfeld,et al.  Hate Online: A Content Analysis of Extremist Internet Sites , 2003 .

[63]  Sung-Hyon Myaeng,et al.  Exploring the user-generated content (UGC) uploading behavior on youtube , 2014, WWW '14 Companion.

[64]  K. Hazel Kwon,et al.  Is offensive commenting contagious online? Examining public vs interpersonal swearing in response to Donald Trump's YouTube campaign videos , 2017, Internet Res..

[65]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[66]  James R. Glass,et al.  Iterative language model estimation: efficient data structure & algorithms , 2008, INTERSPEECH.

[67]  Michael S. Bernstein,et al.  Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions , 2017, CSCW.

[68]  Jeremy Blackburn,et al.  "You Know What to Do" , 2018, Proc. ACM Hum. Comput. Interact..

[69]  Bernard J. Jansen,et al.  Anatomy of Online Hate: Developing a Taxonomy and Machine Learning Models for Identifying and Classifying Hate in Online News Media , 2018, ICWSM.

[70]  Jennifer Jie Xu,et al.  Mining communities and their relationships in blogs: A study of online hate groups , 2007, Int. J. Hum. Comput. Stud..

[71]  Gianluca Stringhini,et al.  What is Gab: A Bastion of Free Speech or an Alt-Right Echo Chamber , 2018, WWW.

[72]  M. Hussin,et al.  Fat stigmatization on YouTube: a content analysis. , 2011, Body image.

[73]  Giovanni Vigna,et al.  Peer to Peer Hate: Hate Speech Instigators and Their Targets , 2018, ICWSM.

[74]  Patricia G. Lange Commenting on YouTube rants: Perceptions of inappropriateness or civic engagement? , 2014 .

[75]  Jordi Luque,et al.  The Role of Linguistic and Prosodic Cues on the Prediction of Self-Reported Satisfaction in Contact Centre Phone Calls , 2017, INTERSPEECH.

[76]  Saleem Alhabash,et al.  To comment or not to comment?: How virality, arousal level, and commenting behavior on YouTube videos affect civic behavioral intentions , 2015, Comput. Hum. Behav..

[77]  Gianluca Stringhini,et al.  Mean Birds: Detecting Aggression and Bullying on Twitter , 2017, WebSci.