BaoNhan/visobert-ViClickbait-2025

ViSoBERT — ViClickbait-2025

Fine-tuned from uitnlp/visobert for binary Vietnamese clickbait detection.

Experimental setup

• Input: headline paired with lead paragraph; no URL, source, category, publish time, image, or engagement metadata.
• Fixed 80/10/10 split using StratifiedGroupKFold with seed 42.
• Fine-tuning seeds: [42, 22, 202]; 3 epochs per seed.
• Development Macro-F1 selects checkpoints and representative seed.
• Weighted cross-entropy from training-label frequencies: True.
• Effective batch size: 8; max length: 256.

Results

Metric	Mean ± sample std
Test Macro-F1	0.7629 ± 0.0039
Test accuracy	0.7788 ± 0.0034
Dev Macro-F1	0.7589 ± 0.0056

Representative seed: 22, selected only by development Macro-F1.

Per-seed

seed	dev_macro_f1	test_macro_f1	test_accuracy
22	0.7645	0.7585	0.7749
42	0.759	0.7655	0.7807
202	0.7534	0.7648	0.7807

Labels

• 0: non-clickbait
• 1: clickbait

Usage

from transformers import AutoModelForSequenceClassification, AutoTokenizer

model_id = "BaoNhan/visobert-ViClickbait-2025"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForSequenceClassification.from_pretrained(model_id)
title = "Tiêu đề bài báo"
lead = "Đoạn dẫn của bài báo"
inputs = tokenizer(title, lead, return_tensors="pt", truncation=True, max_length=256)
prediction = model(**inputs).logits.argmax(dim=-1).item()
print(model.config.id2label[prediction])

Dataset

• Nguyen et al. (2025), ViClickbait-2025: A comprehensive dataset for Vietnamese clickbait detection. https://doi.org/10.1016/j.dib.2025.112164
• Dataset: https://doi.org/10.17632/3wc46bfcjc.1

Limitations

The dataset is small, temporally bounded to 2023–2025, and collected from eight Vietnamese news platforms. Results may not transfer to social media, other publishers, or emerging clickbait styles.