A Socio-Contextual Approach in Automated Detection of Public Cyberbullying on Twitter

Abstract

Cyberbullying is a major cyber issue that is common among adolescents. Recent reports show that more than one out of five students in the United States is a victim of cyberbullying. Majority of cyberbullying incidents occur on public social media platforms such as Twitter. Automated cyberbullying detection methods can help prevent cyberbullying before the harm is done on the victim. In this study, we analyze two corpora of cyberbullying tweets from similar incidents to construct and validate an automated detection model. Our method emphasizes the two claims that are supported by our results. First, despite other approaches that assume that cyberbullying instances use vulgar or profane words, we show that they do not necessarily contain negative words. Second, we highlight the importance of context and the characteristics of actors involved and their position in the network structure in detecting cyberbullying rather than only considering the textual content in our analysis.

Identification of cyber harassment and intention of target users on social media platforms

“… Chatzakou et al (2019) Robust methodology To separate bullies and attackers from regular Twitter users Twitter Textual, User-based, Network-based Classify the accounts with an accuracy of over 90% and an AUC. Tahmasbi and Rastegari (2018) Socio-contextual approach To create and test a model for automatic detection Twitter Textual, Sentimental, Contextual It gives information about several scenarios to detect cyberbullying. …”

A New Security Model for Web Browser Local Storage

“…SOP links the saved information to a specific domain, so the information can only be retrieved from the original domain. When SOP is applied, the browser tests the port number, name of host, and protocol against the source record of the saved data [2].…”

“…HTML5 brought new technologies, such as local storage, web Socket, and enhanced XHR. With these technologies and modules, it has improved the surface of the attack and added new risks to the end-user, which means that the SOP will not help [2]. The weaknesses of SOP led to many aggressions, such as "crosssite scripting (XSS), cross-site request forgeries (CSRF), cross-origin resource sharing (CORS) attacks, social engineering, and physical access" [17].…”

“…When browsing, users expose themselves and their personal information to several threats, such as malware or phishing, which directly disrupt privacy [2]. A user's profile has been the target of many attacks.…”

An Investigation of User Privacy and Data Protection on User-Side Storage

“…Different types of data can be saved in object storage, and it ranges from simple data types (e.g., date, string and array), to classified objects (e.g., JSON and JavaScript Object). It permits objects to be retrieved/ saved with keys [11]. Indexed DB has numerous advantages, like offering fast access to large volumes of structured data, a bigger storage capacity than what's available in other user-side storages, using indexes for effective searches, and the ability to duplicate the values of the keys.…”