Researchers at IIT Roorkee develop sentiment analysis method for Sanskrit texts

Researchers at the Indian Institute of Technology, Roorkee, have developed an efficient method for sentiment analysis of Sanskrit text. The proposed technique has achieved 87.50% accuracy for machine translation and 92.83% accuracy for sentiment classification.

These methods were not fully explored due to the unavailability of sufficient labeled data. The research proposed a method that includes models for machine translation, translation evaluation, and sentiment analysis.

Machine translations have been used as multilingual source and target language mapping. The resulting English translations are mature and natural enough like the original English sentences.

The dataset for conducting this research was taken from the Valmiki Ramayana website which has been developed and maintained by researchers at IIT Kanpur. The researchers plan to explore the morphological properties of Sanskrit for better classification using only root words and their respective suffixes and prefixes.

They also plan to assess whether the morphological richness of Sanskrit is maintained while translating it into English. And they also plan to obtain a model that discerns the context of words in multiple languages ​​and provides word embeddings of smaller dimensions. The model has been published as a research paper in the journal “Applied Intelligence”.

Leave a Comment

+1 631-259-7728
WhatsApp chat +1 631-259-7728
WHATSAPP US, WE'LL RESPOND
WE WRITE YOUR WORK AND ENSURE IT'S PLAGIARISM-FREE.