Common Sense Reasoning for Detection, Prevention, and Mitigation of Cyberbullying

@inproceedings{Dinakar2012CommonSR,
  title={Common Sense Reasoning for Detection, Prevention, and Mitigation of Cyberbullying},
  author={Karthik Dinakar and Rosalind W. Picard and Henry Lieberman},
  booktitle={TIIS},
  year={2012}
}
Cyberbullying (harassment on social networks) is widely recognized as a serious social problem, especially for adolescents. It is as much a threat to the viability of online social networks for youth today as spam once was to email in the early days of the Internet. Current work to tackle this problem has involved social and psychological studies on its prevalence as well as its negative effects on adolescents. While true solutions rest on teaching youth to have healthy personal relationships… 
Cyberbullying Detection in Social Networks: A Multi-Stage Approach
TLDR
The approach proposed in this work views cyberbullying detection as a process of three consecutive stages: aggressive text message detection, alleged aggressor and victim detection, and cyberbullies case detection.
Sentiment Informed Cyberbullying Detection in Social Media
TLDR
The proposed sentiment informed cyberbullying detection framework is motivated by sociological and psychological findings on bullying behaviors and the correlation with emotions, and shows the superiority of the proposed framework on two real-world, publicly available social media datasets.
Automatic Detection and Prevention of Cyberbullying
TLDR
This paper presents the construction and annotation of a corpus of Dutch social media posts annotated with fine-grained cyberbullying-related text categories, such as insults and threats, and describes the specific participants (harasser, victim or bystander) in a cyberbullies conversation to enhance the analysis of human interactions involving cyber Bullying.
Empirical Analysis of Supervised Machine Learning Techniques for Cyberbullying Detection
TLDR
This paper focuses on the implementation of four supervised machine learning methodologies, namely Random Forest, k-Nearest Neighbor, Sequential Machine Optimization, and Naive Bayes in order to identify and detect the presence or absence of cyberbullying in YouTube video comments.
On cyberbullying incidents and underlying online social relationships
Cyberbullying is an important social challenge that takes place over a technical substrate. Thus, it has attracted research interest across both computational and social science research communities.
A Study of Contact Network Generation for Cyber-bullying Detection
  • Mingmei Li, A. Tagami
  • Computer Science
    2014 28th International Conference on Advanced Information Networking and Applications Workshops
  • 2014
TLDR
This paper analyzes the collected SNS data with the actual human relationships, and evaluates the proposed framework to generate a contact network, for the first step of relation-based cyber-bullying detection.
BullyNet: Unmasking Cyberbullies on Social Networks
TLDR
This paper presents a three-phase algorithm, called BullyNet, for detecting cyberbullies on Twitter social network, and proposes a centrality measure to detect cyberbullie from a cyberbullying signed network, which outperforms other existing measures.
Analyzing Negative User Behavior in a Semi-anonymous Social Network
TLDR
This paper studies negative user behavior in the Ask.fm social network, a popular new sitethat has led to many cases of cyberbullying, some leading to suicide, and examines properties of users with “cutting” behavior in this social network.
An Approach to Distinguish Between the Severity of Bullying in Messages in Social Media
TLDR
The authors showed how the severity of the bullying in messages helps to find the real culprit and include a survey on recent algorithms which work on detection of cyberbullying.
Unsupervised Hybrid approaches for Cyberbullying Detection in Instagram
TLDR
The proposed detection method for unsupervised cyberbullying detection method will be extract linguistic attributes such as idioms, sarcasm, irony and active or passive voice from Instagram data set.
...
...

References

SHOWING 1-10 OF 139 REFERENCES
Modeling the Detection of Textual Cyberbullying
TLDR
This work decomposes the overall detection problem into detection of sensitive topics, lending itself into text classification sub-problems and shows that the detection of textual cyberbullying can be tackled by building individual topic-sensitive classifiers.
Let's Gang Up on Cyberbullying
TLDR
The novel design of social network software that can help prevent and manage the growing problem of cyberbullying are discussed.
You Too?! Mixed-Initiative LDA Story Matching to Help Teens in Distress
TLDR
This work examines a corpus of 5500 stories from distressed teenagers from a major youth social network and combines Latent Dirichlet Allocation and human interpretation of its output using principles from sociolinguistics to extract high-level themes in the stories and use them to match new stories to similar ones.
Cyberbullying Prevention and Response
Just as the previous generation was raised in front of televisions, adolescents at the turn of the 21st century are being raised in an internet-enabled world where blogs, social networking, and
Cyberbullying: An Exploratory Analysis of Factors Related to Offending and Victimization
Victimization on the Internet through what has been termed cyberbullying has attracted increased attention from scholars and practitioners. Defined as “willful and repeated harm inflicted through the
Cyberbullying definition and measurement: Some critical considerations
This definition implies that cyberbullying is similar to traditional bullying, but involving the use of new communication technologies. Its hostile trait derives from the aggressive nature of the
Stacked Generalization Learning to Analyze Teenage Distress
TLDR
This paper presents a strategy that combines the strengths of both these types of models inspired by Prevention Science approaches which deals with the identification and amelioration of risk factors that predict to psychological, psychosocial, and psychiatric disorders within and across populations rather than treat them post-facto.
Cyberbullying among youngsters: profiles of bullies and victims
A survey among 2052 primary and secondary school children reveals that cyberbullying among youngsters is not a marginal problem. However, there are discrepancies between the prevalence figures based
Offline Consequences of Online Victimization
Abstract As increasing numbers of youth embrace computer-mediated communication to meet academic and social needs, interpersonal violence directly and indirectly related to the Internet is occurring
...
...