Indonesian Roberta Base Emotion Classifier Open-Source Model - Free Deployment to Boost Indonesian Sentiment Analysis

Indonesian Roberta Base Emotion Classifier

Developed by StevenLimcorn

An Indonesian emotion classifier trained on the Indo-roberta model, fine-tuned on the IndoNLU EmoT dataset for sentiment analysis tasks.

Text Classification

Transformers

OtherOpen Source License:MIT #Indonesian Sentiment Analysis #Multi-label Classification #Transfer Learning Optimization

Downloads 767

Release Time : 3/2/2022

Model Overview

This model is an emotion classifier for Indonesian language, capable of analyzing text and determining its emotional tendency. Based on the RoBERTa architecture, fine-tuned on the IndoNLU EmoT dataset.

Model Features

High-Performance Sentiment Analysis

Achieved a macro F1 score of 72.05% and an accuracy of 71.81% on the IndoNLU benchmark test.

Based on Pre-trained Model

Utilizes the Indo-roberta-base model for transfer learning, leveraging the advantages of pre-trained language models.

Trained on Professional Dataset

Trained on the IndoNLU EmoT professional sentiment analysis dataset to ensure model quality.

Model Capabilities

Indonesian text sentiment analysis

Emotion classification

Use Cases

Social Media Analysis

Social Media Sentiment Monitoring

Analyze the emotional tendency of Indonesian social media content

Can identify positive, negative, and other emotions

Customer Feedback Analysis

Product Review Analysis

Automatically analyze the emotional tendency of Indonesian customer reviews

Helps businesses understand customer satisfaction

🚀 Indo RoBERTa Emotion Classifier

The Indo RoBERTa Emotion Classifier is an emotion classifier built on the Indo-roberta model. It was trained on the IndoNLU EmoT dataset. By leveraging transfer learning, the Indo-roberta model was adapted into an emotion classifier. According to the IndoNLU benchmark, the model achieved an f1-macro of 72.05%, an accuracy of 71.81%, a precision of 72.47%, and a recall of 71.94%.

✨ Features

Based on Robust Model: Utilizes the Indo-roberta model, which provides a solid foundation for emotion classification.
Trained on Quality Data: Trained on the IndoNLU EmoT dataset, ensuring the model's effectiveness in real - world scenarios.
Good Performance Metrics: Achieves high f1 - macro, accuracy, precision, and recall scores as per the IndoNLU benchmark.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import pipeline
pretrained_name = "StevenLimcorn/indonesian-roberta-base-emotion-classifier"
nlp = pipeline(
    "sentiment-analysis",
    model=pretrained_name,
    tokenizer=pretrained_name
)
nlp("Hal-hal baik akan datang.")

📚 Documentation

Model

The model was trained for 7 epochs with a learning rate of 2e - 5. It achieved different metrics as shown in the following table:

Epoch	Training Loss	Validation Loss	Accuracy	F1	Precision	Recall
1	1.300700	1.005149	0.622727	0.601846	0.640845	0.611144
2	0.806300	0.841953	0.686364	0.694096	0.701984	0.696657
3	0.591900	0.796794	0.686364	0.696573	0.707520	0.691671
4	0.441200	0.782094	0.722727	0.724359	0.725985	0.730229
5	0.334700	0.809931	0.711364	0.720550	0.718318	0.724608
6	0.268400	0.812771	0.718182	0.724192	0.721222	0.729195
7	0.226000	0.828461	0.725000	0.733625	0.731709	0.735800

Information Table

Property	Details
Model Type	Emotion classifier based on Indo - roberta model
Training Data	IndoNLU EmoT dataset

Disclaimer

⚠️ Important Note

Consider the biases from both the pre - trained RoBERTa model and the EmoT dataset, which may affect the model's results.

Author

The Indonesian RoBERTa Base Emotion Classifier was trained and evaluated by Steven Limcorn. All computation and development were carried out on Google Colaboratory using their free GPU access.

If used, please cite

@misc {steven_limcorn_2023,
	author       = { {Steven Limcorn} },
	title        = { indonesian-roberta-base-emotion-classifier (Revision e8a9cb9) },
	year         = 2023,
	url          = { https://huggingface.co/StevenLimcorn/indonesian-roberta-base-emotion-classifier },
	doi          = { 10.57967/hf/0681 },
	publisher    = { Hugging Face }
}

📄 License

This project is licensed under the MIT 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