cirimus/modernbert-base-emotions

Overview

This model was fine-tuned from ModernBERT-base on the Super Emotion dataset for multi-class emotion classification. It predicts emotional states in text across seven labels: joy, sadness, anger, fear, love, neutral, surprise.

Model Details

Base Model: ModernBERT-base
Fine-Tuning Dataset: Super Emotion
Number of Labels: 7
Problem Type: Single-label classification
Language: English
License: CC-BY-4.0
Fine-Tuning Framework: Hugging Face Transformers

Example Usage

Here’s how to use the model with Hugging Face Transformers:

from transformers import pipeline

# Load the model
classifier = pipeline(
    "text-classification", 
    model="cirimus/modernbert-base-emotions",
    top_k=5
)

text = "I can't believe this just happened!"
predictions = classifier(text)

# Print top 3 detected emotions
sorted_preds = sorted(predictions[0], key=lambda x: x['score'], reverse=True)
top_3 = sorted_preds[:3]

print("\nTop 3 emotions detected:")
for pred in top_3:
    print(f"\t{pred['label']:10s} : {pred['score']:.3f}")

# Example output:
# Top 3 emotions detected:
#        SURPRISE   : 0.913
#        SADNESS    : 0.033
#        NEUTRAL    : 0.021

How the Model Was Created

The model was fine-tuned for 2 epochs using the following hyperparameters:

Learning Rate: 2e-5
Batch Size: 16
Weight Decay: 0.01
Warmup Steps: Cosine decay scheduling
Optimizer: AdamW
Evaluation Metrics: Precision, Recall, F1 Score (macro), Accuracy

Evaluation Results

As evaluated on the joint test-set:

	Accuracy	Precision	Recall	F1	MCC	Support
macro avg	0.872	0.827	0.850	0.836	0.840	56310
NEUTRAL	0.965	0.711	0.842	0.771	0.755	3907
SURPRISE	0.976	0.693	0.772	0.730	0.719	2374
FEAR	0.975	0.897	0.841	0.868	0.855	5608
SADNESS	0.960	0.910	0.937	0.923	0.896	14547
JOY	0.941	0.933	0.872	0.902	0.861	17328
ANGER	0.964	0.912	0.818	0.862	0.843	7793
LOVE	0.962	0.734	0.867	0.795	0.778	4753

Intended Use

The model is designed for emotion classification in English-language text, particularly useful for:

Social media sentiment analysis
Customer feedback evaluation
Large scale behavioral or psychological research

The model is designed for fast and accurate emotion detection but struggles with subtle expressions or indirect references to emotions (e.g., "I find myself remembering the little things you say, long after you've said them.")

Limitations and Biases

Data Bias: The dataset is aggregated from multiple sources and may contain biases in annotation and class distribution.
Underrepresented Classes: Some emotions have fewer samples, affecting their classification performance.
Context Dependence: The model classifies individual sentences and may not perform well on multi-sentence contexts.

Environmental Impact

Hardware Used: NVIDIA RTX 4090
Training Time: < 1 hour
Carbon Emissions: ~0.04 kg CO2 (estimated via ML CO2 Impact Calculator)

Citation

If you use this model, please cite:

@inproceedings{JdFE2025b,
  title = {Emotion Classification with ModernBERT},
  author = {Enric Junqu\'e de Fortuny},
  year = {2025},
  howpublished = {\url{https://huggingface.co/your_model_name_here}},
}

cirimus
/

modernbert-base-emotions