PhoBERT Sentiment Analysis Fine-tuner
OtherTextFine Tuning
Fine-tuned the PhoBERT model for sentiment analysis on Vietnamese social media comments. The task involved supervised training of the model for accurate emotion/sentiment prediction and comprehensive evaluation using F1-score and ROC-AUC metrics. The main objective was to improve the model's performance on real-world Vietnamese-language text data.
• Collected and prepared text comments from social media for model training and validation.
• Performed fine-tuning of the PhoBERT base model to classify sentiment polarity.
• Evaluated modeling results, achieving an average F1-score of 0.85 and ROC-AUC of 0.92.
• Documented the process and published results on Github.
Fine-tuned the PhoBERT model for sentiment analysis on Vietnamese social media comments. The task involved supervised training of the model for accurate emotion/sentiment prediction and comprehensive evaluation using F1-score and ROC-AUC metrics. The main objective was to improve the model's performance on real-world Vietnamese-language text data. • Collected and prepared text comments from social media for model training and validation. • Performed fine-tuning of the PhoBERT base model to classify sentiment polarity. • Evaluated modeling results, achieving an average F1-score of 0.85 and ROC-AUC of 0.92. • Documented the process and published results on Github.
2025 - 2025