Challenge: Existing methods for CB detection oversimplify the problem of CB as a binary classification task.
Approach: They propose to use large language models to generate CB-related datasets . they propose to combine cognitive and linguistic models to help identify CB incidents .
Outcome: The proposed approach aims to help researchers and policymakers make informed decisions . it uses large language models such as Claude-2 and Llama2-Chat to generate CB-related datasets .

Similar Papers

BullyBench: Youth & Experts-in-the-loop Framework for Intrinsic and Extrinsic Cyberbullying NLP Benchmarking (2025.emnlp-industry)

Copied to clipboard

Challenge: Existing youth-focused CB datasets lack conversational realism and ethical youth involvement with little or no evaluation of their social plausibility.
Approach: They propose a youth-in-the-loop dataset “BullyBench” that incorporates a structured intrinsic quality evaluation with experts-in the-looop (social scientists, psychologists, and content moderators) they perform extrinsic baseline evaluation by benchmarking encoder- and decoder-only language models for multi-class CB role classification.
Outcome: The proposed dataset is evaluated by a team of social scientists, psychologists, and content moderators to assess its quality, relevance, and coherence.
A Just and Comprehensive Strategy for Using NLP to Address Online Abuse (P19-1)

Copied to clipboard

Challenge: Current methods to detect online abuse focus on a narrow definition of abuse to detriment of victims seeking validation and solutions.
Approach: They argue that the NLP community needs to make three substantive changes to tackle both more subtle and more serious forms of abuse.
Outcome: The proposed approach would address the problem of abuse in a more inclusive and productive way.
Mitigating Bias in Session-based Cyberbullying Detection: A Non-Compromising Approach (2021.acl-long)

Copied to clipboard

Challenge: Existing efforts to enhance the performance of session-based cyberbullying detection have overlooked unintended social biases in existing datasets.
Approach: They propose a model-agnostic debiasing strategy that leverages a reinforcement learning technique to mitigate unintended biases in existing datasets.
Outcome: The proposed approach can mitigate unintended biases without impairing the detection performance.
Data Expansion Using WordNet-based Semantic Expansion and Word Disambiguation for Cyberbullying Detection (2022.lrec-1)

Copied to clipboard

Challenge: Existing methods to identify cyberbullying from text are limited due to the complexity of the content and the lack of labeled large-scale corpus.
Approach: They propose a data augmentation-based approach that could enhance the automatic detection of cyberbullying in social media texts.
Outcome: The proposed approach overcomes limitations of social media posts with word sense disambiguation and synonymy relation . results show that the proposed approach improves on the existing classifiers with and without data augmentation.
GenEx: A Commonsense-aware Unified Generative Framework for Explainable Cyberbullying Detection (2023.emnlp-main)

Copied to clipboard

Challenge: a significant gap exists in understanding code-mixed languages and the need for explainability in this context.
Approach: They propose to annotate posts with four labels to identify bullies in code-mixed languages . they propose to use a generative framework to reimagine the multitask problem as a text-to-text generation task.
Outcome: The proposed model outperforms baseline models and state-of-the-art models on the BullyExplain dataset.
BullStop: A Mobile App for Cyberbullying Prevention (2020.coling-demos)

Copied to clipboard

Challenge: Existing tools to combat cyberbullying mostly use wordlists or lack flexibility to cope with the evolving nature of social media.
Approach: BullStop is a mobile app for detecting and preventing cyberbullying and online abuse on social media platforms.
Outcome: BullStop detects and prevents cyberbullying and online abuse on social media platforms and can automatically initiate actions such as deleting offensive messages and blocking bullies on behalf of the user.
Cyberbullying Classifiers are Sensitive to Model-Agnostic Perturbations (2022.lrec-1)

Copied to clipboard

Challenge: toxicity classifiers rely on lexical cues, so creative language use can be detrimental to utility of current corpora and state-of-the-art models.
Approach: They propose to use model-agnostic adversarial behavior to enhance toxic content classification models.
Outcome: The proposed model-agnostic adversarial behavior and augmentation for cyberbullying detection are robust against word-level perturbations at a slight trade-off in overall task performance.
HENIN: Learning Heterogeneous Neural Interaction Networks for Explainable Cyberbullying Detection on Social Media (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for detecting cyberbullying rely on text analysis of social media sessions.
Approach: They propose a deep model that uses a comment encoder and a post-comment co-attention sub-network to explain why a media session is identified as cyberbullying.
Outcome: The proposed model outperforms existing models on real datasets and shows evidential comments in the model explainability of cyberbullying detection.
Meme-ingful Analysis: Enhanced Understanding of Cyberbullying in Memes Through Multimodal Explanations (2024.eacl-long)

Copied to clipboard

Challenge: Recent laws like “right to explanations” have spurred research in developing interpretable models . a recent study has shown that multimodal explanations improve performance in generating textual justifications .
Approach: They propose to use visual and textual modalities to explain why a given meme is cyberbullying . they use a Contrastive Language-Image Pretraining approach to generate textual justifications .
Outcome: The proposed model improves performance in visual and textual explanations and identifies the visual evidence supporting a decision.
Black is to Criminal as Caucasian is to Police: Detecting and Removing Multiclass Bias in Word Embeddings (N19-1)

Copied to clipboard

Challenge: Existing methods to debias word embeddings in binary settings such as gender and religion are limited to binary labels, whereas word2vec embedders can be used to propagate biases.
Approach: They propose a method to debias word embeddings in multiclass settings such as gender and religion, extending the work of Bolukbasi et al. (2016).
Outcome: The proposed method maintains the efficacy in standard NLP tasks while maintaining the utility of embeddings.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations