Publication

Abstract : Sentiment analysis(SA) has become crucial in Natural Language Processing(NLP), allowing valuable perceptions from user-generated content. Aspect-based sentiment analysis(ABSA), focusing on identifying sentiment towards specific aspects, remains challenging, especially for resource-scarce languages like Hindi.  Deep learning has proven effective for ABSA in English, but applying these techniques to Hindi presents challenges due to its complex morphology, limited labeled datasets, and contextual ambiguities. Pre-trained large language models, based on transformer architectures, have become standard for NLP tasks, valuable for low-resource languages.  This paper introduces a hybrid model, Hi-BERT, combining rule-based aspect extraction with a transformer based multilingual BERT architecture for sentiment analysis. Hi-BERT addresses ABSA challenges in Hindi by integrating a POS tagger with a deep learning framework.  The increasing prevalence of online reviews in Hindi necessitates more nuanced sentiment analysis to understand customer feedback effectively. Hi-BERT addresses this by focusing on aspect-level sentiment analysis, extracting aspects using POS tagging, and employing a pre trained multilingual BERT model for multi-class classification. This hybrid approach aims to improve ABSA accuracy in Hindi, offering valuable insights for businesses.