Sentiment Analysis of Code-Mixed Languages Leveraging Resource Rich Languages

Code-mixed data is an important challenge of natural language processing because its characteristics completely vary from the traditional structures standard languages. In this paper, we propose a novel approach called Sentiment Analysis Code-Mixed Text (SACMT) to classify sentences into their corresponding sentiment - positive, negative or neutral, using contrastive learning. We utilize shared parameters siamese networks map code-mixed and languages common space. Also, introduce basic clustering based preprocessing method capture variations transliterated words. Our experiments reveal that SACMT outperforms state-of-the-art approaches in analysis for text by 7.6% accuracy 10.1% F-score.