indobert-emotion

Chipan/indobert-emotion

indobert-emotion is a text classification model from Chipan. Use it when you need a label for a piece of text. It is set up for transformers. The card lists the license as mit.

Downloads · 30 days

3% of all-time downloads

All-time downloads

271

Public

Parameters

124M

498 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors498 MB · 100%

At a glance

Task: Text Classification
Library: transformers
License: mit
Model type: bert
Access: Public
Created: Jun 12, 2025
Updated: Jun 20, 2025
SHA: bb3269f7

Base models

indobenchmark/indobert-base-p1

Datasets

Chipan/indonesia-5-emotion-cls-dataset

Spaces

Chipan/Hexa-API

Model card

From the Hugging Face model README

Emotion Classification Model (Bahasa Indonesia)

This is a fine-tuned IndoBERT-based model for emotion classification in Bahasa Indonesia, designed to classify everyday informal or casual text into one of five emotional categories in bahasa Indonesia. The model is particularly useful for applications involving sentiment analysis, mental health monitoring, journaling platforms, or conversational AI.

🧠 Model Overview

Base Model: indobert-base-p1 (by IndoNLU)
Fine-tuning Task: Multi-class text classification
Number of Classes: 5
Model Format: safetensors
Tokenizer: indobert-base-p1

🏷️ Emotion Classes

The model is trained to classify input text into one of the following five emotions:

Emotion	Description
Marah	Angry, Frustation
Sedih	Sadness, disappointment
Senang	Joy, excitement
Stress	Anxiety, mental pressure
Bersyukur	Gratitude, thankfulness

⚠️ Limitations

Best performance on informal Indonesian (conversational, daily tone)
May struggle with sarcasm, code-switching (mix of Indonesian-English), or domain-specific jargon

Task: Text Classification
Library: transformers
Type: bert
License: mit
Languages: id
Created: Jun 12, 2025
Updated: Jun 20, 2025