arndri/indobertweet-finetuned-indonlu-smsa

IndoBERTweet finetuned with IndoNLU smsa_doc-sentiment-prosa (Positive and Negative Sentiment Only)

Training Details

Epoch	Training Loss	Validation Loss
1	0.149900	0.139475
2	0.131600	0.143117
3	0.036600	0.192144

Evaluation

Class	Precision	Recall	F1-Score	Support
Positive	0.98	0.94	0.96	1098
Negative	0.89	0.96	0.93	601
Accuracy	0.95			1699
Macro Avg	0.93	0.95	0.94	1699
Weighted Avg	0.95	0.95	0.95	1699

Citation

If you use this model, please cite:

A. Pratama and M. Rosyda, “ANALISIS SENTIMEN DALAM APLIKASI X TERHADAP PENGUNGSI ROHINGYA DENGAN LSTM”, SKANIKA, vol. 8, no. 1, pp. 95-105, Jan. 2025.