• Corpus ID: 18025046

Improved cyberbullying detection using gender information

  title={Improved cyberbullying detection using gender information},
  author={Maral Dadvar and Franciska de Jong and Roeland Ordelman and Dolf Trieschnigg},
As a result of the invention of social networks, friendships, relationships and social communication are all undergoing changes and new definitions seem to be applicable. One may have hundreds of ‘friends’ without even seeing their faces. Meanwhile, alongside this transition there is increasing evidence that online social applications are used by children and adolescents for bullying. State-of-the-art studies in cyberbullying detection have mainly focused on the content of the conversations… 

Figures and Tables from this paper

Cyberbullying detection: a step toward a safer internet yard

This work proposes that incorporation of the users' information, their characteristics, and post-harassing behaviour, for instance, posting a new status in another social network as a reaction to their bullying experience, will improve the accuracy of cyberbullying detection.

Mining Patterns of Cyberbullying on Twitter

A detailed analysis of a large–scale real–world dataset is performed to identify online social network topology structure features that are the most prominent in enhancing the accuracy of state–of–the–art classification methods for cyberbullying detection.

Detection of Cyberbullying in Social Networks Using Machine Learning Methods

  • Elif Varol AltayB. Alatas
  • Computer Science
    2018 International Congress on Big Data, Deep Learning and Fighting Cyber Terrorism (IBIGDELFT)
  • 2018
The use of natural language processing techniques and machine learning methods namely, Bayesian logistic regression, random forest algorithm, multilayer sensor, J48 algorithm and support vector machines have been used to determine cyber bullying.

Cyberbullying Detection in Social Networks: A Multi-Stage Approach

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.

Detection of cyberbullying on social media messages in Turkish

It is observed that when both words and emoticons in the text messages are taken into account as features, cyberbully detection improves and Naïve Bayes Multinomial is the most successful one in terms both classification accuracy and running time.

Automatic detection of cyberbullying on social media platforms

The method for selecting the best features for two different classifiers trained on datasets collected from Twitter and Formspring is described and the predictions made by these classifiers for labelling a new dataset collected by us from Twitter.

A review of cyberbullying detection: An overview

This paper illustrates a survey covering some methods and challenges in cyberbullying and offers suggestions for continued research in this area.


The experimental results of the study proved that SGD and MLP classifiers with 500 selected features using SVM-RFE algorithm showed the best results by means of classification time and accuracy.

Social Media Cyberbullying Detection using Machine Learning

A supervised machine learning approach for detecting and preventing cyberbullying and shows that Neural Network performs better and achieves accuracy of 92.8% and NN outperforms other classifiers of similar work on the same dataset.

Detecting Cyberbullying Activity Across Platforms

A large corpus with 800,000 instances of cell phone textual data from youth ages 10–14 has been developed to address the need for authentic data for studying communication with and among youth and machine learning algorithms are shown to be effective at detecting cyberbullying across platforms.



Modeling the Detection of Textual Cyberbullying

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.

Cyberbullying: its nature and impact in secondary school pupils.

Two studies found cyberbullying less frequent than traditional bullying, but appreciable, and reported more outside of school than inside, and being a cybervictim, but not a cyberbully, correlated with internet use.

Cyber Bullying: An Old Problem in a New Guise?

  • M. Campbell
  • Political Science
    Australian Journal of Guidance and Counselling
  • 2005
Abstract Although technology provides numerous benefits to young people, it also has a ‘dark side’, as it can be used for harm, not only by some adults but also by the young people themselves.

Text Classification Techniques Used to Faciliate Cyber Terrorism Investigation

This research aims to create text classification system which classifies the document using several algorithms including Naïve Bayes, Nearest Neighbor, Support Vector Machine (SVM), Decision Tree, and Multilayer Perceptron, and the result shows that SVM outperforms by achieving 100% of accuracy.

Detection of Harassment on Web 2.0

This paper uses a supervised learning approach for harassment that employs content features, sentiment features, and contextual features of documents and achieves significant improvements over several baselines, including Term Frequency- Inverse Document Frequency (TFIDF) approaches.

Cyberspace Violence against Girls and Adolescent Females

An overview of the developments in cyberspace is given, different types of cyberviolence are described, and cyberbullying among girls and adolescent females as both victims and perpetrators of cyberbullies are focused on.

ChatCoder: Toward the Tracking and Categorization of Internet Predators

The software used to facilitate analysis of chat log transcripts and the development of a communicative theory of online predation is presented, which shows that one can distinquish between predator and victim communication, but not as reliably as one would like to.

Research on School Bullying and Victimization: What Have We Learned and Where Do We Go From Here?

Abstract This special issue on bullying and victimization in School Psychology Review highlights current research efforts in American schools on bullying and peer victimization, and how this research


Using data from two real-world applications, it is empirically showed that the proposed co-classification framework is more effective that learning to classify the Web spam and spammers independently.

Automatic Vandalism Detection in Wikipedia : Towards a Machine Learning Approach

This study investigates the possibility of using machine learning techniques to build an autonomous system capable to distinguish vandalism from legitimate edits and reveals that elementary features are not sufficient to build such a system.