On cyberbullying incidents and underlying online social relationships

Abstract

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. While the social science studies conducted via careful participant selection have shown the effect of personality, social relationships, and psychological factors on cyberbullying, they are often limited in scale due to manual survey or ethnographic study components. Computational approaches on the other hand have defined multiple automated approaches for detecting cyberbullying at scale, and have largely focused only on the textual content of the messages exchanged. There are no existing efforts aimed at testing, validating, and potentially refining the findings from traditional bullying literature as obtained via surveys and ethnographic studies at scale over online environments. By analyzing the social relationship graph between users in an online social network and deriving features such as out-degree centrality and the number of common friends, we find that multiple social characteristics are statistically different between the cyberbullying and nonbullying groups, thus supporting many, but not all, of the results found in previous survey-based bullying studies. The results pave way for better understanding of the cyberbullying phenomena at scale.

Assessing the Surge in COVID-19-Related Cyberbullying on Twitter: A Generalized Additive Model Approach

“…The broader literature on cyberbullying trends, especially during global crises (Lopez-Meneses et al, 2020), we observe that our findings largely align with the consensus that online harassment incidents tend to escalate during periods of heightened global stress. Several studies have similarly reported spikes in cyberbullying during past global events (Wang et al, 2020;Saravanaraj et al, 2016;Huang et al, 2018), albeit on different platforms or regions. While our study primarily focused on Twitter data within a specific timeframe, other research might consider a wider range of platforms or longer periods (Das et al, 2020).…”

A Creativity Survey of Cyberbullying Classification Based on Social Network Analysis

“…Traditional detection methods are trained by published content, so most of the extant articles use this approach. However, experimental methods with a user perspective have also emerged, specifically by analyzing individual user information, language patterns, and user-user interactivity to detect verbal bullying [13].…”

Comprehensive Analysis of Privacy Attacks in Online Social Network: Security Issues and Challenges

“…Each OSN has its own rules and dataset for sharing data within group users only. So, it is significant issues that how we should secure our confidential information on the online social network from intruders [25].…”