Rapid Cyber-bullying detection method using Compact BERT Models

Nowadays, many people use their social media platform to spread hate online and that is why the problem of cyber-bullying detection has been the focus of many researchers over the past decade. In this work, we tackle this problem with transfer learning. We use various compact BERT models and fine-tu...

Full description

Saved in:
Bibliographic Details
Published in2021 IEEE 15th International Conference on Semantic Computing (ICSC) pp. 199 - 202
Main Authors Behzadi, Mitra, Harris, Ian G., Derakhshan, Ali
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.01.2021
Subjects
Bit error rate
Compact BERT
Cyber-bulling
Focal Loss
Hate-Speech
Pipelines
Real-time systems
Reliability
Semantics
Social networking (online)
Transfer learning
Online AccessGet full text
DOI10.1109/ICSC50631.2021.00042

Cover

More Information
Summary:Nowadays, many people use their social media platform to spread hate online and that is why the problem of cyber-bullying detection has been the focus of many researchers over the past decade. In this work, we tackle this problem with transfer learning. We use various compact BERT models and fine-tune them with hate-speech data. We incorporate Focal Loss function to handle class imbalance in the data. Using this approach, we were able to achieve state-of-the-art results of 0.91 precision, 0.92 recall and 0.91 F1-score on the hate-speech dataset. Additionally, using our transfer learning pipeline, we show that the more compact BERT models are significantly faster in detection and are suitable for real-time applications of cyber-bullying detection.
DOI:10.1109/ICSC50631.2021.00042