Sentiment classification for telugu using transformed based approaches on a multi-domain dataset

Abstract Sentiment analysis is an essential component of Natural Language Processing (NLP) in resource-abundant languages such as English. Nevertheless, poor-resource languages such as Telugu have experienced limited efforts owing to multiple considerations, such as a scarcity of corpora for trainin...

Full description

Saved in:
Bibliographic Details
Main Authors: Kannaiah Chattu, K. Adi Narayana Reddy, Sai babu veesam, Pardha Saradhi Chirumamilla, Vunnava Dinesh Babu, Krishna Prakash, Shonak Bansal, Mohammad Rashed Iqbal Faruque, K. S. Al-mugren
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-05703-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849335287586488320
author Kannaiah Chattu
K. Adi Narayana Reddy
Sai babu veesam
Pardha Saradhi Chirumamilla
Vunnava Dinesh Babu
Krishna Prakash
Shonak Bansal
Mohammad Rashed Iqbal Faruque
K. S. Al-mugren
author_facet Kannaiah Chattu
K. Adi Narayana Reddy
Sai babu veesam
Pardha Saradhi Chirumamilla
Vunnava Dinesh Babu
Krishna Prakash
Shonak Bansal
Mohammad Rashed Iqbal Faruque
K. S. Al-mugren
author_sort Kannaiah Chattu
collection DOAJ
description Abstract Sentiment analysis is an essential component of Natural Language Processing (NLP) in resource-abundant languages such as English. Nevertheless, poor-resource languages such as Telugu have experienced limited efforts owing to multiple considerations, such as a scarcity of corpora for training machine learning models and an absence of gold standard datasets for evaluation. The current surge of transformed based models in NLP enables the attainment of exceptional performance in many different tasks. Nevertheless, researchers are increasingly interested in exploring the potential of transformed based models that have been pre-trained in several languages for various natural language processing applications, particularly for languages with limited resources. This research examines the efficacy of four pre-trained transformed based models, specifically IndicBERT, RoBERTa, DeBERTa, and XLM-RoBERTa, for sentence-level sentiment analysis in the Telugu language. Evaluated the performance of all four models using our dataset, “Sentikanna,” which consists of numerous domain datasets for the Telugu language. We compared the performance of these models with three different datasets and observed a promising outcome. XLM-RoBERTa achieves a good accuracy of 79.42% for a binary sentiment classification. This work can be considered a reliable standard for sentiment analysis in the Telugu language.
format Article
id doaj-art-97819503264640c58dc45e89dfd78aa9
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-97819503264640c58dc45e89dfd78aa92025-08-20T03:45:19ZengNature PortfolioScientific Reports2045-23222025-07-0115112110.1038/s41598-025-05703-9Sentiment classification for telugu using transformed based approaches on a multi-domain datasetKannaiah Chattu0K. Adi Narayana Reddy1Sai babu veesam2Pardha Saradhi Chirumamilla3Vunnava Dinesh Babu4Krishna Prakash5Shonak Bansal6Mohammad Rashed Iqbal Faruque7K. S. Al-mugren8Department of Computer Science & Engineering (AIML), Malla Reddy College of Engineering & TechnologyDepartment of Computer Science & Engineering, Faculty of Science and Technology (IcfaiTech), ICFAI Foundation for Higher Education (IFHE)School of Computer Science and Engineering, VIT-AP UniversitySenior Software Engineer, Unicon Systems IncDepartment of CSE, RV Institute of TechnologyDepartment of Electronics and Communication, NRI Institute of TechnologyDepartment of Electronics and Communication Engineering, Chandigarh UniversitySpace Science Centre (ANGKASA), Institute of Climate Change (IPI), Universiti Kebangsaan MalaysiaPhysics department, Science College, Princess Nourah bint Abdulrahman UniversityAbstract Sentiment analysis is an essential component of Natural Language Processing (NLP) in resource-abundant languages such as English. Nevertheless, poor-resource languages such as Telugu have experienced limited efforts owing to multiple considerations, such as a scarcity of corpora for training machine learning models and an absence of gold standard datasets for evaluation. The current surge of transformed based models in NLP enables the attainment of exceptional performance in many different tasks. Nevertheless, researchers are increasingly interested in exploring the potential of transformed based models that have been pre-trained in several languages for various natural language processing applications, particularly for languages with limited resources. This research examines the efficacy of four pre-trained transformed based models, specifically IndicBERT, RoBERTa, DeBERTa, and XLM-RoBERTa, for sentence-level sentiment analysis in the Telugu language. Evaluated the performance of all four models using our dataset, “Sentikanna,” which consists of numerous domain datasets for the Telugu language. We compared the performance of these models with three different datasets and observed a promising outcome. XLM-RoBERTa achieves a good accuracy of 79.42% for a binary sentiment classification. This work can be considered a reliable standard for sentiment analysis in the Telugu language.https://doi.org/10.1038/s41598-025-05703-9Sentiment classificationNatural Language processingTelugu LanguageTransformed based modelsXLM-RoBERTa
spellingShingle Kannaiah Chattu
K. Adi Narayana Reddy
Sai babu veesam
Pardha Saradhi Chirumamilla
Vunnava Dinesh Babu
Krishna Prakash
Shonak Bansal
Mohammad Rashed Iqbal Faruque
K. S. Al-mugren
Sentiment classification for telugu using transformed based approaches on a multi-domain dataset
Scientific Reports
Sentiment classification
Natural Language processing
Telugu Language
Transformed based models
XLM-RoBERTa
title Sentiment classification for telugu using transformed based approaches on a multi-domain dataset
title_full Sentiment classification for telugu using transformed based approaches on a multi-domain dataset
title_fullStr Sentiment classification for telugu using transformed based approaches on a multi-domain dataset
title_full_unstemmed Sentiment classification for telugu using transformed based approaches on a multi-domain dataset
title_short Sentiment classification for telugu using transformed based approaches on a multi-domain dataset
title_sort sentiment classification for telugu using transformed based approaches on a multi domain dataset
topic Sentiment classification
Natural Language processing
Telugu Language
Transformed based models
XLM-RoBERTa
url https://doi.org/10.1038/s41598-025-05703-9
work_keys_str_mv AT kannaiahchattu sentimentclassificationforteluguusingtransformedbasedapproachesonamultidomaindataset
AT kadinarayanareddy sentimentclassificationforteluguusingtransformedbasedapproachesonamultidomaindataset
AT saibabuveesam sentimentclassificationforteluguusingtransformedbasedapproachesonamultidomaindataset
AT pardhasaradhichirumamilla sentimentclassificationforteluguusingtransformedbasedapproachesonamultidomaindataset
AT vunnavadineshbabu sentimentclassificationforteluguusingtransformedbasedapproachesonamultidomaindataset
AT krishnaprakash sentimentclassificationforteluguusingtransformedbasedapproachesonamultidomaindataset
AT shonakbansal sentimentclassificationforteluguusingtransformedbasedapproachesonamultidomaindataset
AT mohammadrashediqbalfaruque sentimentclassificationforteluguusingtransformedbasedapproachesonamultidomaindataset
AT ksalmugren sentimentclassificationforteluguusingtransformedbasedapproachesonamultidomaindataset