Assessing Text Classification Methods for Cyberbullying Detection on Social Media Platforms

2024-12-27

AI Summary

To address poor real-time performance, low data quality, high computational overhead, and insufficient model generalization in social media cyberbullying detection, this study develops a lightweight, efficient text-based detection system tailored for real-world deployment. We conduct the first systematic, multi-dimensional evaluation—comparing accuracy, F1-score, inference latency, memory footprint, and energy consumption—of five transformer-based models (BERT, RoBERTa, XLNet, DistilBERT, and GPT-2.0) on cyberbullying identification. Results show that supervised fine-tuned BERT achieves 95% accuracy and F1-score, with per-instance inference time of 0.053 seconds, memory usage of 35.28 MB, and energy consumption of 0.000263 kWh—demonstrating superior overall efficiency. These findings challenge the prevailing assumption that generative models inherently outperform discriminative ones in this task, and provide a reproducible, scalable technical pathway for deploying cyberbullying detection on resource-constrained social platforms.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Diffusion Models for Vision

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Cyberbullying significantly contributes to mental health issues in communities by negatively impacting the psychology of victims. It is a prevalent problem on social media platforms, necessitating effective, real-time detection and monitoring systems to identify harmful messages. However, current cyberbullying detection systems face challenges related to performance, dataset quality, time efficiency, and computational costs. This research aims to conduct a comparative study by adapting and evaluating existing text classification techniques within the cyberbullying detection domain. The study specifically evaluates the effectiveness and performance of these techniques in identifying cyberbullying instances on social media platforms. It focuses on leveraging and assessing large language models, including BERT, RoBERTa, XLNet, DistilBERT, and GPT-2.0, for their suitability in this domain. The results show that BERT strikes a balance between performance, time efficiency, and computational resources: Accuracy of 95%, Precision of 95%, Recall of 95%, F1 Score of 95%, Error Rate of 5%, Inference Time of 0.053 seconds, RAM Usage of 35.28 MB, CPU/GPU Usage of 0.4%, and Energy Consumption of 0.000263 kWh. The findings demonstrate that generative AI models, while powerful, do not consistently outperform fine-tuned models on the tested benchmarks. However, state-of-the-art performance can still be achieved through strategic adaptation and fine-tuning of existing models for specific datasets and tasks.

Problem

• cyberbullying detection
• text classification
• efficiency

Innovation

• Traditional Tokenization Optimization
• BERT Model
• Cyberbullying Detection