| ---
|
| language:
|
| - id
|
| - ace
|
| - ban
|
| - bjn
|
| - bug
|
| - jav
|
| - mad
|
| - min
|
| - sun
|
| - bbc
|
| - eng
|
| library_name: transformers
|
| pipeline_tag: text-classification
|
| tags:
|
| - text-classification
|
| - hate-speech-detection
|
| - abusive-language-detection
|
| - multilabel-classification
|
| - indonesian
|
| - multilingual
|
| - social-media
|
| - natural-language-processing
|
| - xlm-roberta
|
| license: apache-2.0
|
| metrics:
|
| - accuracy
|
| - f1
|
| base_model:
|
| - FacebookAI/xlm-roberta-base
|
| ---
|
|
|
| # Hate Speech & Abusive Language Detection (Multilabel)
|
| **Multilingual Indonesian & English — XLM-RoBERTa**
|
|
|
| This repository provides a fine-tuned **XLM-RoBERTa** model for **MULTILABEL HATE CONTENT DETECTION** in social media text.
|
| The model is designed to identify **Hate Speech** and **Abusive Language** simultaneously across **Indonesian**, **regional Indonesian languages**, and **English**, particularly in noisy and informal online conversations.
|
|
|
| ---
|
|
|
| ## 🚀 Highlights
|
|
|
| - Multilabel classification: **Hate Speech** & **Abusive Language**
|
| - Supports overlapping labels in a single text
|
| - Multilingual (Indonesia + English)
|
| - Robust on informal and user-generated content
|
| - Ready-to-use with Hugging Face `pipeline`
|
| - Suitable for content moderation and safety systems
|
|
|
| ---
|
|
|
| ## 🌍 Supported Languages
|
|
|
| - 🇮🇩 Bahasa Indonesia
|
| - Bahasa Melayu
|
| - Indonesian regional languages (Aceh, Banjar, Bugis, Jawa, Madura, Minang, Sunda, dll.)
|
| - 🇬🇧 English
|
|
|
| ---
|
|
|
| ## 📊 Model Performance
|
|
|
| > Performance metrics are reported on a held-out validation set.
|
|
|
| | Metric | Score |
|
| |-----------------|--------|
|
| | Precision | 0.9249 |
|
| | Recal | 0.9300 |
|
| | F1 (Macro) | 0.9274 |
|
| | F1 (Weighted) | 0.9269 |
|
| | Training Loss | 0.1181 |
|
| | Validation Loss | 0.2070 |
|
|
|
| *(Exact scores may vary depending on evaluation split and threshold.)*
|
|
|
| ---
|
|
|
| ## ⚙️ Usage
|
|
|
| ### Installation
|
| ```bash
|
| pip install transformers torch
|
| ````
|
|
|
| ### Single Prediction
|
|
|
| ```python
|
| from transformers import pipeline
|
|
|
| classifier = pipeline(
|
| task="text-classification",
|
| model="nahiar/hatespeech-abusive-xlm-roberta-v1",
|
| return_all_scores=True
|
| )
|
|
|
| result = classifier("Dasar bodoh, otak udang!")
|
| print(result)
|
| ```
|
|
|
| **Output**
|
|
|
| ```text
|
| [
|
| {'label': 'HATESPEECH', 'score': 0.9123},
|
| {'label': 'ABUSIVE', 'score': 0.9841}
|
| ]
|
| ```
|
|
|
| > Because this is a **multilabel model**, more than one label can be active for a single input.
|
|
|
| ---
|
|
|
| ## 🏷️ Label Definitions
|
|
|
| ```text
|
| HATESPEECH → Content that attacks or demeans a group based on identity
|
| ABUSIVE → Insulting, offensive, or aggressive language without protected targets
|
| ```
|
|
|
| ---
|
|
|
| ## 📦 Batch Inference
|
|
|
| ```python
|
| texts = [
|
| "Dasar kaum ini selalu bikin rusuh",
|
| "Kamu memang bodoh dan tidak berguna",
|
| "Saya tidak setuju dengan pendapat kamu"
|
| ]
|
|
|
| results = classifier(texts)
|
|
|
| for text, preds in zip(texts, results):
|
| labels = [(p["label"], round(p["score"], 4)) for p in preds]
|
| print(text, "→", labels)
|
| ```
|
|
|
| ---
|
|
|
| ## 🏗️ Training Configuration
|
|
|
| | Parameter | Value |
|
| | ----------------- | ------------------------- |
|
| | Base Model | xlm-roberta-base |
|
| | Task Type | Multilabel Classification |
|
| | Training Strategy | Fine-tuning |
|
| | Epochs | Multiple |
|
| | Learning Rate | 2e-5 |
|
| | Batch Size | 16 |
|
| | Training Date | 2025-12-18 |
|
|
|
| ---
|
|
|
| ## 🎯 Intended Use
|
|
|
| * Hate speech & abusive language moderation
|
| * Content safety and compliance systems
|
| * Social media monitoring dashboards
|
| * Pre-filtering before sentiment or topic analysis
|
|
|
| ---
|
|
|
| ## ⚠️ Limitations
|
|
|
| * Limited to **Hate Speech** and **Abusive Language** labels
|
| * Does not identify specific hate targets or protected attributes
|
| * Context-dependent sarcasm may be misclassified
|
| * Not suitable for legal or policy enforcement without human review
|
|
|
| ---
|
|
|
| ## 📜 License
|
|
|
| This model is released under the **Apache License 2.0**
|
| Free for research and commercial use.
|
|
|
| ---
|
|
|
| ## 📚 Citation
|
|
|
| ```bibtex
|
| @misc{djunaedi2025hatespeech_multilabel,
|
| author = {Raihan Hidayatulloh Djunaedi},
|
| title = {Multilabel Hate Speech and Abusive Language Detection for Social Media Text},
|
| year = {2025},
|
| publisher = {Hugging Face},
|
| url = {https://huggingface.co/nahiar/hatespeech-xlmr-v4}
|
| }
|
| ```
|
|
|
| ---
|
|
|
| ## 🙌 Acknowledgements
|
|
|
| * Hugging Face Transformers
|
| * Facebook AI Research — XLM-RoBERTa |
