Downloads · 30 days
4
6% of all-time downloads
distilbert-emotion-ekman-mbti
akrvnka/distilbert-emotion-ekman-mbti
distilbert-emotion-ekman-mbti is a machine learning model from akrvnka. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Model ini adalah hasil fine-tuning distilbert-base-uncased untuk klasifikasi 6 emosi dasar Ekman (angry, disgust, fear, happy, sad, surprise) dari teks Twitter, sebagai bagian dari penelitian Tugas Akhir tentang klasi…
All-time downloads
63
Public
Parameters
67M
268 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors268 MB · 100%
At a glance
- License
- apache-2.0
- Model type
- distilbert
- Access
- Public
- Created
- Jul 19, 2026
- Updated
- Jul 19, 2026
- SHA
- 7061eff0
Model card
From the Hugging Face model README
DistilBERT Fine-tuned for Ekman Emotion Classification
Model ini adalah hasil fine-tuning distilbert-base-uncased untuk klasifikasi 6 emosi dasar Ekman
(angry, disgust, fear, happy, sad, surprise) dari teks Twitter, sebagai bagian dari penelitian
Tugas Akhir tentang klasifikasi kepribadian MBTI berbasis distribusi emosi.
Performa Model (Data Uji)
- Accuracy: 0.9042
- Precision (macro): 0.8723
- Recall (macro): 0.9081
- F1-score (macro): 0.8890
Cara Pakai
from transformers import pipeline
clf = pipeline("text-classification", model="akrvnka/distilbert-emotion-ekman-mbti")
clf("I am so excited for tomorrow!")
Training Detail
- Base model: distilbert-base-uncased
- Epochs: 12 (dengan early stopping, load_best_model_at_end)
- Learning rate: 2e-5
- Batch size: 32
- Class weighting diterapkan untuk menangani ketidakseimbangan kelas
- Dataset: Twitter Reviews for Emotion Analysis (train:val:test = 70:15:15, stratified)
- Type
- distilbert
- License
- apache-2.0
- Languages
- en
- Created
- Jul 19, 2026
- Updated
- Jul 19, 2026