Skip to main content

Thursday, 21 November 2024 | 03:53 pm

|   Subscribe   |   donation   Support Us    |   donation

Log in
Register


"Preaching is the expression of moral sentiment in application to the duties of life": IIT Roorkee Researchers develop a Sentiments Analysis Method for Sanskrit Text, achieved 87.50% accuracy for machine translation and 92.83% for sentiment classification

The proposed sentiment analysis model comprises a machine translation model, a translation evaluation model, and a sentiment analysis model
 |  Satyaagrah  |  Sanatan
IIT Roorkee Researchers Develop A Sentiments Analysis Method For Sanskrit Text
IIT Roorkee Researchers Develop A Sentiments Analysis Method For Sanskrit Text

New Delhi: The Indian Institute of Technology (IIT) Roorkee researchers have developed an efficient method for Sanskrit text sentiment analysis. The proposed technique has achieved 87.50 percent accuracy for machine translation and 92.83 percent accuracy for sentiment classification.

This research of IIT Roorkee proposed a method that comprises models for machine translation, translation evaluation, and sentiment analysis.

The team involved in this research are Professor Balasubramanian Raman, Department of Computer Science and Engineering and his Ph.D. student Mr. Puneet Kumar, and his MSc student Mr. Kshitij Pathania, Department of Mathematics.

The machine translations have been used as cross-lingual mapping of the source and the target language. The obtained English translations are sufficiently mature and natural as the original English sentences. The model has been published as a research paper in a reputed peer-reviewed journal Applied Intelligence.

Elaborating on the sentiment analysis model, Professor Balasubramanian Raman, Department of Computer Science, IIT Roorkee, said, "We have trained our model to predict sentiment scores in the range of positive, neutral, or negative. And the model uses statistics, natural language processing, and machine learning to determine the sentiment with over 90 percent accuracy."

The dataset to perform this research was taken from the Valmiki Ramayana website developed and maintained by the IIT Kanpur researchers.

The future plans of the researchers are to exploit the morphological properties of Sanskrit for better classification using only root words with their respective suffixes and prefix.

It is also planned to evaluate whether the morphological richness of Sanskrit is retained while translating to English. Moreover, the researchers also plan to obtain a model that discerns the context of words in multiple languages and provides word embeddings of lesser dimensions.

References:

ndtv.com

Support Us


Satyagraha was born from the heart of our land, with an undying aim to unveil the true essence of Bharat. It seeks to illuminate the hidden tales of our valiant freedom fighters and the rich chronicles that haven't yet sung their complete melody in the mainstream.

While platforms like NDTV and 'The Wire' effortlessly garner funds under the banner of safeguarding democracy, we at Satyagraha walk a different path. Our strength and resonance come from you. In this journey to weave a stronger Bharat, every little contribution amplifies our voice. Let's come together, contribute as you can, and champion the true spirit of our nation.

Satyaagrah Razorpay PayPal
 ICICI Bank of SatyaagrahRazorpay Bank of SatyaagrahPayPal Bank of Satyaagrah - For International Payments

If all above doesn't work, then try the LINK below:

Pay Satyaagrah

Please share the article on other platforms

To Top

DISCLAIMER: The author is solely responsible for the views expressed in this article. The author carries the responsibility for citing and/or licensing of images utilized within the text. The website also frequently uses non-commercial images for representational purposes only in line with the article. We are not responsible for the authenticity of such images. If some images have a copyright issue, we request the person/entity to contact us at This email address is being protected from spambots. You need JavaScript enabled to view it. and we will take the necessary actions to resolve the issue.


Related Articles