EMOTIBERT: SENTIMENTAL ANALYSIS FOR REVIEW SENTIMENT ANALYSIS OF CUSTOMER REVIEWS FOR ACCURATE PERCEPTION PREDICTION

This study introduces an innovative sentiment analysis framework for textual reviews by utilizing the
Bidirectional Encoder Representations from Transformers (BERT) model in combination with a
customized syntax-aware BERT variant. Both models are optimized using the AdamW algorithm to
achieve faster convergence and better generalization. Furthermore, the integration of the spaCy dependency parser enriches syntactic comprehension, thereby enhancing sentiment classification performance. Experimental evaluation on standard benchmark datasets reveals that the proposed syntax-enhanced BERT significantly surpasses the baseline BERT model in terms of precision, recall,
and F1-score, confirming the advantage of incorporating syntactic features into transformer-based
sentiment analysis systems.