mbert-lv-emotions-ekman

AiLab-IMCS-UL/mbert-lv-emotions-ekman

mbert-lv-emotions-ekman is a machine learning model from AiLab-IMCS-UL. 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.

A fine-tuned version of Multilingual BERT for multi-label text classification of six basic emotions (+neutral) in Latvian, as defined by Ekman’s theory.

Downloads · 30 days

3% of all-time downloads

All-time downloads

279

Public

Parameters

178M

1.4 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors711 MB · 99%

At a glance

License: apache-2.0
Model type: bert
Access: Public
Created: Sep 13, 2024
Updated: Nov 10, 2025
SHA: b17fa139

Base models

google-bert/bert-base-multilingual-cased

Datasets

Model card

From the Hugging Face model README

Latvian Basic Emotion Classifier

A fine-tuned version of Multilingual BERT for multi-label text classification of six basic emotions (+neutral) in Latvian, as defined by Ekman’s theory.

The model is trained on a combined dataset of go_emotions-lv and twitter_emotions-lv.

Predicted labels:

0: anger
1: disgust
2: fear
3: joy
4: sadness
5: surprise
6: neutral

The random seed used for initialization was 42:

def set_seed(seed=42):
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)
    if torch.cuda.is_available():
        torch.cuda.manual_seed_all(seed)

Training parameters:

max_length: null
batch_size: 32
shuffle: True
num_workers: 4
pin_memory: False
drop_last: False
optimizer: adam
lr: 0.00001
weight_decay: 0
problem_type: multi_label_classification
num_epochs: 4

Evaluation

Evaluation results on the test split of go_emotions-lv:

	Precision	Recall	F1-Score	Support
anger	0.50	0.35	0.41	726
disgust	0.44	0.28	0.35	123
fear	0.58	0.47	0.52	98
joy	0.80	0.76	0.78	2104
sadness	0.66	0.41	0.51	379
surprise	0.59	0.55	0.57	677
neutral	0.71	0.43	0.54	1787
micro avg	0.70	0.55	0.62	5894
macro avg	0.61	0.46	0.52	5894
weighted avg	0.69	0.55	0.61	5894
samples avg	0.58	0.56	0.57	5894

Evaluation results on the test split of twitter_emotions-lv:

	Precision	Recall	F1-Score	Support
anger	0.92	0.88	0.90	12013
disgust	0.90	0.94	0.92	14117
fear	0.82	0.67	0.74	3342
joy	0.88	0.84	0.86	5913
sadness	0.86	0.75	0.80	4786
surprise	0.94	0.56	0.70	1510
micro avg	0.90	0.85	0.87	41681
macro avg	0.76	0.66	0.70	41681
weighted avg	0.90	0.85	0.87	41681
samples avg	0.85	0.85	0.85	41681

Acknowledgements

This work was supported by the EU Recovery and Resilience Facility project Language Technology Initiative (2.3.1.1.i.0/1/22/I/CFLA/002).

Type: bert
License: apache-2.0
Languages: lv
Created: Sep 13, 2024
Updated: Nov 10, 2025