SCOPE

With the advancement of electronics and information technologies, digital media platforms and virtual space have become a significant part of human life today. People can share and exchange information and ideas globally just with a single click. Among these digital media platforms, social networks such as Facebook, YouTube, Twitter, etc., have a good standing. They represent the most used applications by the people, everywhere and for all times so far. Moreover, the traffic generated by digital media platforms represents more than half of the web traffic worldwide. 

It is a fact that the use of these digital media platforms has dramatically influenced our habits on the Internet and in our daily life. As a result, we must adequately be wary of the electronic violence propagated via social networks. Indeed, cyberbullying has recently emerged as an effective form of bullying and online harassment. This phenomenon is becoming a concern worldwide. It includes many forms such as racism, terrorism, and several types of trolling. On the other hand, Machine Intelligence (MI) and overall Artificial Intelligence have shown promise to be powerful tools in various domains, such as computer vision, natural language processing (NLP), speech recognition, computational biology, and others. Motivated by these successes, researchers worldwide have recently started investigating applications of these techniques to handle cyberbullying issues in the modern media. In this context, in recent years, many methods such as Fuzzy Logic (FL), Evolutionary Algorithms (EA), Machine Learning (ML), Artificial Neural Networks (ANN) and Deep Learning (DL) have been applied for detecting cyberbullying content generated by digital media platforms. This book examines how machine intelligence techniques can contribute to detecting and combating cyberbullying phenomenon. 

The book is intended for researchers, specialists in AI and cyberbullying, teachers and it could be helpful for undergraduate and graduate students as well.

TOPICS

Cyberbullying: State-of-the-Art Survey

• Overview of Machine Learning Techniques

• Overview Deep Learning Techniques

• Overview on Cyberbullying Features Detection/Prevention

• Cyberbullying in Online Unstructured Data

• Cyberbullying sources and Social Media

Artificial Intelligence for Cyberbullying detection

• Machine Learning and Ensemble Learning Approaches

• Deep Learning Models

• Text-Mining and Sentiment Analysis Techniques

• Graph Optimization Algorithms

• Explainable Artificial Intelligence

• Cyberbullying Detection Techniques and Coronavirus Epidemic.

Cyberbullying prevention techniques

• Machine Learning and Ensemble Learning

• Deep Learning

• Text-Mining and Sentiment Analysis Techniques

• Graph Optimization Algorithms

• Explainable Artificial Intelligence

• Cyberbullying Prevention Techniques and Coronavirus Epidemic.

Feature engineering on Cyberbullying

• Linguistics, Writing Style and Sentiment Based Features

• Social-Context Based and User’ Information Based Features

• Feature Selection, Extraction, Construction and Reduction

• Feature Analysis on Cyberbullying  Detection/Prevention

Solutions and frameworks in the practice

• Benchmark Dataset for Cyberbullying Detection/Prevention

• Real-World System for Cyberbullying Detection/Prevention

• BlockChain Technology on Cyberbullying

• Tracking and aggregating Online Cyberbullying

• Cyberbullying and Social Media

• New Trends on News for Cyberbullying