peace_bert Open-source Covert Hate Speech Detector - Focused on Precise Detection of Harmful Information in English Content

Peace Bert

Developed by BenjaminOcampo

This model is a BERT-architecture optimized implicit hate speech detector, specifically trained and fine-tuned for English implicit hate speech.

Text Classification

Transformers

English#Implicit hate detection #High-precision F1 #English context optimization

Downloads 26

Release Time : 7/30/2024

Model Overview

This model is used to detect implicit hate speech in English, with a particular focus on identifying covert hate content on social media and online platforms.

Model Features

Implicit hate speech detection

Specifically optimized for more covert implicit hate speech rather than overt hate expressions.

Trained on ISHate dataset

Trained using a specialized dataset focused on implicit hate speech, enhancing the model's ability to recognize such content.

Balanced performance

Optimized through metrics like F1 score and accuracy to achieve a balance between detection accuracy and comprehensiveness.

Model Capabilities

Text classification

Hate speech detection

Implicit content identification

Use Cases

Content moderation

Social media content moderation

Automatically identify implicit hate speech on social media platforms

Improve content moderation efficiency and reduce manual review workload

Academic research

Hate speech research

Used to analyze linguistic features and propagation patterns of implicit hate speech

🚀 Implicit Hate Speech Detection Model

This is a hate speech detector fine - tuned for implicit hate speech detection, based on the paper presented at the 27th European Conference on Artificial Intelligence.

🚀 Quick Start

This README provides detailed information about an implicit hate speech detection model, including its base model, training datasets, parameters, evaluation results, and authors.

✨ Features

Specifically fine - tuned for detecting implicit hate speech.
Based on the research paper "PEACE: Providing Explanations and Analysis for Combating Hate Expressions".
Evaluated using standard metrics such as F1 score and accuracy.

📦 Installation

No installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

No code examples are provided in the original document, so this section is skipped.

📚 Documentation

Model Information

Base Model: BenjaminOcampo/model-bert__trained-in-ishate__seed-0
Library Name: transformers
License: bsl - 1.0
Tags: hate - speech - detection, implicit - hate - speech

Property	Details
Model Type	A hate speech detector fine - tuned for implicit hate speech
Training Data	ISHate dataset (training part focusing on implicit hate speech)

Training Parameters and Experimental Info

The model was trained using the ISHate dataset, concentrating on implicit data. The training parameters were as follows:

Batch size: 32
Weight decay: 0.01
Epochs: 4
Learning rate: 2e - 5

For detailed information on the training process, please refer to the model's paper.

Datasets

The model was trained on the ISHate dataset, specifically the training part of the dataset which focuses on implicit hate speech.

Evaluation Results

The model's performance was evaluated using standard metrics, including F1 score and accuracy. For comprehensive evaluation results, refer to the linked paper.

Authors

🔧 Technical Details

The model is based on the paper "PEACE: Providing Explanations and Analysis for Combating Hate Expressions" by Greta Damo, Nicolás Benjamín Ocampo, Elena Cabrio, and Serena Villata, presented at the 27th European Conference on Artificial Intelligence. This model card documents the demo paper "PEACE: Providing Explanations and Analysis for Combating Hate Expressions" accepted at the 27th European Conference on Artificial Intelligence: https://www.ecai2024.eu/calls/demos.

📄 License

The model is licensed under the bsl - 1.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご