Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Role Identification based Method for Cyberbullying Analysis in Social Edge Computing

Runyu Wang, Tun Lu, Peng Zhang, Ning Gu

TL;DR

This paper tackles fine-grained cyberbullying role identification in social edge computing by proposing DEK, a differential evolution-assisted K-means clustering method designed for mixed categorical-continuous data. It builds a three-layer feature model (content-based, sentiment-based, and user-based) from Sina Weibo data and demonstrates nine distinct cyberbullying roles across ten real-world scenarios. DEK outperforms a range of clustering baselines on public and real-world datasets and enables analysis of role evolution, distributions, and influencing factors under different scenarios and interventions. The work advances real-time, edge-driven monitoring and intervention for cyberbullying, with potential for broader platform coverage and improved governance, while noting computational and methodological limitations to guide future enhancements.

Abstract

Over the past few years, many efforts have been dedicated to studying cyberbullying in social edge computing devices, and most of them focus on three roles: victims, perpetrators, and bystanders. If we want to obtain a deep insight into the formation, evolution, and intervention of cyberbullying in devices at the edge of the Internet, it is necessary to explore more fine-grained roles. This paper presents a multi-level method for role feature modeling and proposes a differential evolution-assisted K-means (DEK) method to identify diverse roles. Our work aims to provide a role identification scheme for cyberbullying scenarios for social edge computing environments to alleviate the general safety issues that cyberbullying brings. The experiments on ten real-world datasets obtained from Weibo and five public datasets show that the proposed DEK outperforms the existing approaches on the method level. After clustering, we obtained nine roles and analyzed the characteristics of each role and their evolution trends under different cyberbullying scenarios. Our work in this paper can be placed in devices at the edge of the Internet, leading to better real-time identification performance and adapting to the broad geographic location and high mobility of mobile devices.

Role Identification based Method for Cyberbullying Analysis in Social Edge Computing

TL;DR

This paper tackles fine-grained cyberbullying role identification in social edge computing by proposing DEK, a differential evolution-assisted K-means clustering method designed for mixed categorical-continuous data. It builds a three-layer feature model (content-based, sentiment-based, and user-based) from Sina Weibo data and demonstrates nine distinct cyberbullying roles across ten real-world scenarios. DEK outperforms a range of clustering baselines on public and real-world datasets and enables analysis of role evolution, distributions, and influencing factors under different scenarios and interventions. The work advances real-time, edge-driven monitoring and intervention for cyberbullying, with potential for broader platform coverage and improved governance, while noting computational and methodological limitations to guide future enhancements.

Abstract

Over the past few years, many efforts have been dedicated to studying cyberbullying in social edge computing devices, and most of them focus on three roles: victims, perpetrators, and bystanders. If we want to obtain a deep insight into the formation, evolution, and intervention of cyberbullying in devices at the edge of the Internet, it is necessary to explore more fine-grained roles. This paper presents a multi-level method for role feature modeling and proposes a differential evolution-assisted K-means (DEK) method to identify diverse roles. Our work aims to provide a role identification scheme for cyberbullying scenarios for social edge computing environments to alleviate the general safety issues that cyberbullying brings. The experiments on ten real-world datasets obtained from Weibo and five public datasets show that the proposed DEK outperforms the existing approaches on the method level. After clustering, we obtained nine roles and analyzed the characteristics of each role and their evolution trends under different cyberbullying scenarios. Our work in this paper can be placed in devices at the edge of the Internet, leading to better real-time identification performance and adapting to the broad geographic location and high mobility of mobile devices.
Paper Structure (30 sections, 11 equations, 4 figures, 4 tables, 1 algorithm)

This paper contains 30 sections, 11 equations, 4 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Cyberbullying detection
  4. Social role identification
  5. Summary
  6. Research Site: Sina Weibo
  7. Feature Engineering
  8. Content-based features
  9. Sentiment-based features
  10. User-based features
  11. Method for Role Identification
  12. K-means and differential evolution
  13. Proposed approach
  14. Motivation
  15. Clustering optimization objective and data continuity operation
  16. ...and 15 more sections

Figures (4)

  • Figure 1: Distribution of occupied number of roles involved in cyberbullying.
  • Figure 2: Changes in the number of members occupied in roles over time in ten scenarios. (a) Scenario 1, (b) Scenario 2, (c) Scenario 3, (d) Scenario 4, (e) Scenario 5, (f) Scenario 6, (g) Scenario 7, (h) Scenario 8, (i) Scenario 9, (j) Scenario 10. The abscissa represents time while the ordinate represents the percentage of people occupied in different roles.
  • Figure 3: Detail of the shaded section in Fig. \ref{['Fig2']}\ref{['Fig2a']} - \ref{['Fig2']}\ref{['Fig2e']}. (a) Scenario 1, (b) Scenario 2, (c) Scenario 3, (d) Scenario 4, (e) Scenario 5. The abscissa represents time while the ordinate represents the number of people occupied in different roles.
  • Figure 4: Detail of the shaded section in Fig. \ref{['Fig2']}\ref{['Fig2f']} - \ref{['Fig2']}\ref{['Fig2j']}. (a) Scenario 6, (b) Scenario 7, (c) Scenario 8, (d) Scenario 9, (e) Scenario 10. The abscissa represents time while the ordinate represents the number of people occupied in different roles.