Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Weakly supervised cyberbullying detection with participant-vocabulary consistency

Weakly supervised cyberbullying detection with participant-vocabulary consistency Online harassment and cyberbullying are becoming serious social health threats damaging people’s lives. This phenomenon is creating a need for automated, data-driven techniques for analyzing and detecting such detrimental online behaviors. We propose a weakly supervised machine learning method for simultaneously inferring user roles in harassment-based bullying and new vocabulary indicators of bullying. The learning algorithm considers social structure and infers which users tend to bully and which tend to be victimized. To address the elusive nature of cyberbullying using minimal effort and cost, the learning algorithm only requires weak supervision. The weak supervision is in the form of expert-provided small seed of bullying indicators, and the algorithm uses a large, unlabeled corpus of social media interactions to extract bullying roles of users and additional vocabulary indicators of bullying. The model estimates whether each social interaction is bullying based on who participates and based on what language is used, and it tries to maximize the agreement between these estimates, i.e., participant-vocabulary consistency (PVC). To evaluate PVC, we perform extensive quantitative and qualitative experiments on three social media datasets: Twitter, Ask.fm, and Instagram. We illustrate the strengths and weaknesses of the model by analyzing the identified conversations and key phrases by PVC. In addition, we demonstrate the distributions of bully and victim scores to examine the relationship between the tendencies of users to bully or to be victimized. We also perform fairness evaluation to analyze the potential for automated detection to be biased against particular groups. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Social Network Analysis and Mining Springer Journals

Weakly supervised cyberbullying detection with participant-vocabulary consistency

Download PDF
17 pages

Loading next page...
 
/lp/springer_journal/weakly-supervised-cyberbullying-detection-with-participant-vocabulary-PEW5eHwla8
Publisher
Springer Journals
Copyright
Copyright © 2018 by Springer-Verlag GmbH Austria, part of Springer Nature
Subject
Computer Science; Data Mining and Knowledge Discovery; Applications of Graph Theory and Complex Networks; Game Theory, Economics, Social and Behav. Sciences; Statistics for Social Science, Behavorial Science, Education, Public Policy, and Law; Methodology of the Social Sciences
ISSN
1869-5450
eISSN
1869-5469
DOI
10.1007/s13278-018-0517-y
Publisher site
See Article on Publisher Site

Abstract

Online harassment and cyberbullying are becoming serious social health threats damaging people’s lives. This phenomenon is creating a need for automated, data-driven techniques for analyzing and detecting such detrimental online behaviors. We propose a weakly supervised machine learning method for simultaneously inferring user roles in harassment-based bullying and new vocabulary indicators of bullying. The learning algorithm considers social structure and infers which users tend to bully and which tend to be victimized. To address the elusive nature of cyberbullying using minimal effort and cost, the learning algorithm only requires weak supervision. The weak supervision is in the form of expert-provided small seed of bullying indicators, and the algorithm uses a large, unlabeled corpus of social media interactions to extract bullying roles of users and additional vocabulary indicators of bullying. The model estimates whether each social interaction is bullying based on who participates and based on what language is used, and it tries to maximize the agreement between these estimates, i.e., participant-vocabulary consistency (PVC). To evaluate PVC, we perform extensive quantitative and qualitative experiments on three social media datasets: Twitter, Ask.fm, and Instagram. We illustrate the strengths and weaknesses of the model by analyzing the identified conversations and key phrases by PVC. In addition, we demonstrate the distributions of bully and victim scores to examine the relationship between the tendencies of users to bully or to be victimized. We also perform fairness evaluation to analyze the potential for automated detection to be biased against particular groups.

Journal

Social Network Analysis and Mining – Springer Journals

Published: Jun 1, 2018

References

  • The five W’s of bullying on Twitter: who, what, why, where, and when
    Bellmore, A; Calvin, AJ; Xu, J-M; Zhu, X
  • It’s complicated
    Boyd, D
  • Cyberbullying or cyber aggression? A review of existing definitions of cyber-based peer-to-peer aggression
    Corcoran, L; Guckin, CM; Prentice, G
  • Identity and deception in the virtual community
    Donath, JS
  • The role of power imbalance in cyberbullying
    Dordolo, N
  • Understanding and preventing bullying
    Farrington, DP
  • Cyber violence: recognizing and resisting abuse in online environments
    Herring, SC
  • Cyberbullying: bullying in the digital age
    Kowalski, RM; Limber, SP; Agatston, PW
  • Introduction to information retrieval
    Manning, CD; Raghavan, P; Schütze, H
  • Incorporating query expansion and quality indicators in searching microblog posts
    Massoudi, K; Tsagkias, M; Rijke, M; Weerkamp, W
  • Learning to identify internet sexual predation
    McGhee, I; Bayzick, J; Kontostathis, A; Edwards, L; McBride, A; Jakubowski, E
  • An effective approach for cyberbullying detection
    Nahar, V; Li, X; Pang, C
  • Cyberbullying prevention and response: expert perspectives
    Patchin, JW; Hinduja, S
  • Linguistic inquiry and word count: LIWC
    Pennebaker, JW; Francis, ME; Booth, RJ
  • Beyond vandalism: wikipedia trolls
    Shachaf, P; Ha, N
  • Cyberbullying: its nature and impact in secondary school pupils
    Smith, PK; Mahdavi, J; Carvalho, M; Fisher, S; Russell, S; Tippett, N
  • Following you home from school: a critical review and synthesis of research on cyberbullying victimization
    Tokunaga, RS
  • School bullying among US adolescents: physical, verbal, relational and cyber
    Wang, J; Iannotti, RJ; Nansel, TR
  • A survey of the nature and extent of bullying in junior/middle and secondary schools
    Whitney, I; Smith, PK