arndri/indobertweet-finetuned-indonlu-smsa

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

Training Details

<table border="1"> <thead> <tr> <th>Epoch</th> <th>Training Loss</th> <th>Validation Loss</th> </tr> </thead> <tbody> <tr> <td>1</td> <td>0.149900</td> <td>0.139475</td> </tr> <tr> <td>2</td> <td>0.131600</td> <td>0.143117</td> </tr> <tr> <td>3</td> <td>0.036600</td> <td>0.192144</td> </tr> </tbody> </table>

Evaluation

<!-- This section describes the evaluation protocols and provides the results. -->

<table border="1"> <thead> <tr> <th>Class</th> <th>Precision</th> <th>Recall</th> <th>F1-Score</th> <th>Support</th> </tr> </thead> <tbody> <tr> <td>Positive</td> <td>0.98</td> <td>0.94</td> <td>0.96</td> <td>1098</td> </tr> <tr> <td>Negative</td> <td>0.89</td> <td>0.96</td> <td>0.93</td> <td>601</td> </tr> <tr> <td colspan="5"></td> </tr> <tr> <td>Accuracy</td> <td colspan="3">0.95</td> <td>1699</td> </tr> <tr> <td>Macro Avg</td> <td>0.93</td> <td>0.95</td> <td>0.94</td> <td>1699</td> </tr> <tr> <td>Weighted Avg</td> <td>0.95</td> <td>0.95</td> <td>0.95</td> <td>1699</td> </tr> </tbody> </table>

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.