• Corpus ID: 86867275

Cyberbullying Detection based on Semantic- Enhanced Marginalized Denoising Auto-Encoder

  title={Cyberbullying Detection based on Semantic- Enhanced Marginalized Denoising Auto-Encoder},
  author={Dasari Swathi and S. Babu},
Social Networking is a group of Internet based applications that allow the creation and exchange of user-generated content. Via social media, people can enjoy enormous information, convenient communication experience and so on. Since, social media may have some side effects such as cyberbullying, which may have negative impacts on the life of people, especially children and teenagers. Cyberbullying can be defined as aggressive, intentional actions performed by an individual or a group of people… 

Figures from this paper

Building towards Automated Cyberbullying Detection: A Comparative Analysis

A comparative analysis of the automated cyberbullying techniques from different perspectives is discussed including data annotation, data preprocessing, and feature engineering and the importance of emojis in expressing emotions as well as their influence on sentiment classification and text comprehension is discussed.

Cyberbullying Detection in Social Networks Using Bi-GRU with Self-Attention Mechanism

This work proposes a complete model combining the bidirectional gated recurrent unit (Bi-GRU) and the self-attention mechanism for text-based cyberbullying detection and shows that the proposed method outperformed baselines in all evaluation metrics.

Cyberbullying Detection, Based on the FastText and Word Similarity Schemes

A new detection algorithm is proposed based on FastText and word similarity schemes that can effectively improve the detection accuracy and recall rate of cyberbullying detection.

Cyberbullying detection on social multimedia using soft computing techniques: a meta-analysis

This work is a systematic literature review to gather, explore, comprehend and analyze the research trends, gaps and prospects of this alliance of using soft computing techniques for cyberbullying detection on social multimedia using a meta-analytic approach.

Session-based Cyberbullying Detection in Social Media: A Survey

This survey paper defines the Session-based Cyberbullying Detection framework that encapsulates the different steps and challenges of the problem, and provides a comprehensive overview of session-based cyberbullying detection in social media, delving into existing efforts from a data and methodological perspective.

Detection of Cyberbullying using Machine Learning

  • C. Sinchana
  • Computer Science
    International Journal for Research in Applied Science and Engineering Technology
  • 2020
The main objective of this project is to detect cyberbullying by matching both Image and Textual data.

Automatic detection of cyberbullying in social media text

This paper describes the collection and fine-grained annotation of a cyberbullying corpus for English and Dutch and performs a series of binary classification experiments to determine the feasibility of automatic cyberbullies detection.

Cyberbullying detection on multi-modal data using pre-trained deep learning architectures

This paper used RoBERTa and Xception deep learning architectures to generate word embeddings from the text data and the image respectively and efficiently classifies bullying data with F1-score of 80% and outperforms as compared to existing approaches.


A new text representation model based on a variant of SDA: marginalized stacked denoising auto encoders (mSDA), which adopts linear instead of nonlinear projection to accelerate training and marginalizes infinite noise distribution in order to learn more robust representations.

Survey of Cyberbulling Detection on Social Media Big-Data

: Opinion mining or sentiment analysis is considered as an important application of NLP (Natural Language Processing). Opinion mining is extracting the views that people express online. Those



An Effective Approach for Cyberbullying Detection

An effective approach to detect cyberbullying messages from social media through a weighting scheme of feature selection is proposed and a graph model is presented to extract the cyberBullying network, which is used to identify the most active cyberbullies predators and victims through ranking algorithms.

Detecting Offensive Language in Social Media to Protect Adolescent Online Safety

  • Ying ChenYilu ZhouSencun ZhuHeng Xu
  • Computer Science
    2012 International Conference on Privacy, Security, Risk and Trust and 2012 International Confernece on Social Computing
  • 2012
This work proposes the Lexical Syntactic Feature (LSF) architecture to detect offensive content and identify potential offensive users in social media, and incorporates a user's writing style, structure and specific cyber bullying content as features to predict the user's potentiality to send out offensive content.

Impact of Usage of Social Networking Sites on Youth: An Overview

Social Networking Sites (SNS) is a buzz word in today’s world due to its enormous growth, customer base and usage. The main focus of this paper is to present an insight into impact of SNS usage on

Issues and Challenges of Cyber Security for Social Networking Sites (Facebook)

A survey is conducted to find users view regarding security and privacy of social networking sites and regarding default privacy setting improvement particularly Facebook.

A Normative Agent System to Prevent Cyberbullying

  • T. BosseS. Stam
  • Computer Science
    2011 IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology
  • 2011
The results show that the normative agents have the potential to reduce the amount of norm violations on the long term.

Improving Cyberbullying Detection with User Context

It is shown that taking user context into account improves the detection of cyberbullying.

Cyber Crime: Critical View

An overview on cyber crime and the ethical issues related to this field and the issues connected to the massive increase in cyber crime ratio are reviewed.

J.I.Sheeba, “Online Social Network Bullying Detection

  • Using Intelligence Techniques”,
  • 2015