Multilingual Exploration of the Kambaramayana: Analyzing Tamil Translations in Telugu, Malayalam, and Kannada Using mBERT and DistilBERT

An essential and basic aspect of our existence are our emotions. Our behaviors and words reflect our feelings, even though they are not instantly obvious. This research looks at the multilingual features of the Kambaramayana, with a concentration on Tamil translates into Telugu, Malayalam, and Kannada. We study how linguistic and cultural subtleties show across translations using a varied dataset. We do a comparison study using sophisticated multilingual language models, specifically mBERT and DistilBERT, to identify semantic variances and similarities. We hope to uncover the subtle interplay among language and culture in literary text transmission by investigating vocabulary, grammar, and cultural allusions. Our findings not only improve the accuracy of cross-lingual text analysis, but also highlight the Ramayana's lasting relevance among South Indian language communities. The experiments clearly reveal that mBERT outperforms DistilBERT in emotion analysis tasks between languages.