skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Detecting LGBTQ+ Instances of Cyberbullying
Social media continues to have an impact on the trajectory of humanity. However, its introduction has also weaponized keyboards, allowing the abusive language normally reserved for in-person bullying to jump onto the screen, i.e., cyberbullying. Cyberbullying poses a significant threat to adolescents globally, affecting the mental health and well-being of many. A group that is particularly at risk is the LGBTQ+ community, as researchers have uncovered a strong correlation between identifying as LGBTQ+ and suffering from greater online harassment. Therefore, it is critical to develop machine learning models that can accurately discern cyberbullying incidents as they happen to LGBTQ+ members. The aim of this study is to compare the efficacy of several transformer models in identifying cyberbullying targeting LGBTQ+ individuals. We seek to determine the relative merits and demerits of these existing methods in addressing complex and subtle kinds of cyberbullying by assessing their effectiveness with real social media data.  more » « less
Award ID(s):
2227488 2036127
PAR ID:
10572838
Author(s) / Creator(s):
; ; ; ;
Publisher / Repository:
The International Conference on Social Computing, Behavioral-Cultural Modeling & Prediction and Behavior Representation in Modeling and Simulation (SBP-BRiMS)
Date Published:
Subject(s) / Keyword(s):
Cyberbullying LGBTQ+ Social Media LLMs
Format(s):
Medium: X
Location:
Pittsburgh, PA, USA
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; (, The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP))
    null (Ed.)
    The element of repetition in cyberbullying behavior has directed recent computational studies toward detecting cyberbullying based on a social media session. In contrast to a single text, a session may consist of an initial post and an associated sequence of comments. Yet, emerging efforts to enhance the performance of session-based cyberbullying detection have largely overlooked unintended social biases in existing cyberbullying datasets. For example, a session containing certain demographic-identity terms (e.g., “gay” or “black”) is more likely to be classified as an instance of cyberbullying. In this paper, we first show evidence of such bias in models trained on sessions collected from different social media platforms (e.g., Instagram). We then propose a context-aware and model-agnostic debiasing strategy that leverages a reinforcement learning technique, without requiring any extra resources or annotations apart from a pre-defined set of sensitive triggers commonly used for identifying cyberbullying instances. Empirical evaluations show that the proposed strategy can simultaneously alleviate the impacts of the unintended biases and improve the detection performance. 
    more » « less
  2. ; ; ; ; ; (, The 5th Workshop on Computational Methods in Online Misbehavior (CyberSafety). In Companion Proceedings of the ACM Web Conference 2020 (WWW).)
    Concurrent with the growth and widespread use of social networking platforms has been a rise in the prevalence of cyberbullying and cyberharassment, particularly among youth. Although cyberbullying is frequently defined as hostile communication or interactions that occur repetitively via electronic media, little is known about the temporal aspects of cyberbullying on social media, such as how the number, frequency, and timing of posts may vary systematically between cyberbullying and non-cyberbullying social media sessions. In this paper, we aim to contribute to the understanding of temporal properties of cyberbullying through the analysis of Instagram data. That is, the paper presents key temporal characteristics of cyberbullying and trends obtained from descriptive and burst analysis tasks. Our results have the potential to inform the development of more effective cyberbullying detection models. 
    more » « less
  3. ; ; ; ; (, The 12th ACM International Conference on Web Search and Data Mining (WSDM))
    Over the last decade, research has revealed the high prevalence of cyberbullying among youth and raised serious concerns in society. Information on the social media platforms where cyberbullying is most prevalent (e.g., Instagram, Facebook, Twitter) is inherently multi-modal, yet most existing work on cyberbullying identification has focused solely on building generic classification models that rely exclusively on text analysis of online social media sessions (e.g., posts). Despite their empirical success, these efforts ignore the multi-modal information manifested in social media data (e.g., image, video, user profile, time, and location), and thus fail to offer a comprehensive understanding of cyberbullying. Conventionally, when information from different modalities is presented together, it often reveals complementary insights about the application domain and facilitates better learning performance. In this paper, we study the novel problem of cyberbullying detection within a multi-modal context by exploiting social media data in a collaborative way. This task, however, is challenging due to the complex combination of both cross-modal correlations among various modalities and structural dependencies between different social media sessions, and the diverse attribute information of different modalities. To address these challenges, we propose XBully, a novel cyberbullying detection framework, that first reformulates multi-modal social media data as a heterogeneous network and then aims to learn node embedding representations upon it. Extensive experimental evaluations on real-world multi-modal social media datasets show that the XBully framework is superior to the state-of-the-art cyberbullying detection models. 
    more » « less
  4. ; ; ; ; ; (, The 2024 International Conference on Advances in Social Networks Analysis and Mining (ASONAM))
    Social media discourse involves people from different backgrounds, beliefs, and motives. Thus, often such discourse can devolve into toxic interactions. Generative Models, such as Llama and ChatGPT, have recently exploded in popularity due to their capabilities in zero-shot question-answering. Because these models are increasingly being used to ask questions of social significance, a crucial research question is whether they can understand social media dynamics. This work provides a critical analysis regarding generative LLM’s ability to understand language and dynamics in social contexts, particularly considering cyberbullying and anti-cyberbullying (posts aimed at reducing cyberbullying) interactions. Specifically, we compare and contrast the capabilities of different large language models (LLMs) to understand three key aspects of social dynamics: language, directionality, and the occurrence of bullying/anti-bullying messages. We found that while fine-tuned LLMs exhibit promising results in some social media understanding tasks (understanding directionality), they presented mixed results in others (proper paraphrasing and bullying/anti-bullying detection). We also found that fine-tuning and prompt engineering mechanisms can have positive effects in some tasks. We believe that a understanding of LLM’s capabilities is crucial to design future models that can be effectively used in social applications. 
    more » « less
  5. ; ; ; ; (, Frontiers in Psychiatry)
    null (Ed.)
    Previous research has identified a link between mental health and cyberbullying, primarily in studies of youth. Fewer studies have examined cyberbullying in adults or how the relation between mental health and cyberbullying might vary based on an individual's social media use. The present research examined how three indicators of mental health—depression, anxiety, and substance use—interact with social media use and gender to predict cyberbullying in adults. In Study 1, U.S. adults recruited through Amazon Mechanical Turk ( N = 525) completed an online survey that included measures of mental health and cyberbullying. Multiple regression analyses revealed significant three-way interactions between mental health, degree of social media use, and gender in models predicting cyberbullying victimization and perpetration. Specifically, for men, depression and anxiety predicted greater cyberbullying victimization and perpetration, particularly among men with relatively higher levels of social media use. In contrast, depression and anxiety were uncorrelated with cyberbullying for women, regardless of level of social media use. Study 2 largely replicated these findings using well-validated measures of mental health (e.g., Center for Epidemiological Studies-Depression scale, Beck Anxiety Inventory, Global Appraisal of Individual Needs Substance Use scale) in U.S. adults recruited through Prolific.co ( N = 482). Together, these results underscore the importance of examining mental health correlates of cyberbullying within the context of social media use and gender and shed light on conditions in which indicators of mental health may be especially beneficial for predicting cyberbullying in adults. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email