Subalalitha Chinnaudayar Navaneethakrishnan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Subalalitha Chinnaudayar Navaneethakrishnan has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Bharathi Raja Chakravarthi
School of Computer Science, University of Galway, Galway, Ireland
5 shared publications - Prasanna Kumar Kumaresan
Unit for Inclusive Artificial Intelligence, Insight Research Ireland Centre for Data Analytics, Data Science Institute, School of Computer Science, University of Galway, Galway, Ireland
5 shared publications - Bharathi Bhagavathsingh
Department of Computer Science and Engineering, Sri Sivasubramaniya Nadar College of Engineering, Chennai, India
3 shared publications - R. Nithya
Government Arts and Science College (Co-Ed)
3 shared publications - Sathiyaraj Thangasamy
Department of Tamil, Sri Krishna Adithya College of Arts and Science, Kovaipudur, India
3 shared publications - A. Vinoth
SRI KRISHNA ADITHYA COLLEGE OF ARTS AND SCIENCE
2 shared publications
Latest Publications
- Open Access
- 19 August 2026
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 16 (1)
Multi-agent framework for span-level detection of homophobic and transphobic comments in Hindi
Social media platforms serve as spaces for both open expression and the spread of harmful narratives, often targeting marginalized communities. In the context of Hindi, automated detection of homophobic and transphobic comments at span level is still not studied widely. This work introduces a span-annotated dataset of Hindi social media comments, where identity-based toxic comments are labeled at the span level using character-based indices and encoded in BIO (Begin, Inside, Outside) format to support token-level classification. To address the scarcity of annotated resources, we adopt a human-in-the-loop framework that combines expert-labeled seed data with systematically generated synthetic data using GPT-4o prompting, followed by human validation to ensure cultural and contextual accuracy. We proposed novel augmentation strategies for annotation homophobic/transphopic at the span level which incorporates context-level, entity-level, combined context/entity, and noise-level strategies, enabling richer and more diverse training material. The dataset was built in three stages: a seed version, an intermediate augmented version, and a final version. We benched-marked our dataset with multiple prompting strategies, including zero-shot, few-shot, and augmentation-based approaches, across both vanilla and cooperative multi-agent framework. Our proposed multi-agent framework decomposes the detection process into specialized roles such as self-annotation, span-related feature extraction, demonstration scoring, and final prediction, resulting in a structured and interpretable pipeline for span-level homophobic/transphobic speech detection. Experiments are conducted on both the test split and the combined extended test set, with evaluation using strict token-level, hybrid, and span-overlap metrics to capture both exact and tolerant boundary matches. Our proposed multi-agent framework using augmented V3 data on the combined extended test set, achieved a Macro F1 score of 0.90 , outperforming the strongest single-agent baseline and demonstrating the effectiveness of combining augmentation, multi-agent reasoning, and refined evaluation. Disclaimer: This study includes examples of toxic language strictly for research and educational purposes. The content does not reflect the views of the authors. Reader discretion is advised. GitHub Link: https://github.com/Unit-for-Inclusive-AI/Multi-Agent-HT-Span-Hindi
- 19 August 2026
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 16 (1)
Open AccessMulti-agent framework for span-level detection of homophobic and transphobic comments in Hindi
Social media platforms serve as spaces for both open expression and the spread of harmful narratives, often targeting marginalized communities. In the context of Hindi, automated detection of homophobic and transphobic comments at span level is still not studied widely. This work introduces a span-annotated dataset of Hindi social media comments, where identity-based toxic comments are labeled at the span level using character-based indices and encoded in BIO (Begin, Inside, Outside) format to support token-level classification. To address the scarcity of annotated resources, we adopt a human-in-the-loop framework that combines expert-labeled seed data with systematically generated synthetic data using GPT-4o prompting, followed by human validation to ensure cultural and contextual accuracy. We proposed novel augmentation strategies for annotation homophobic/transphopic at the span level which incorporates context-level, entity-level, combined context/entity, and noise-level strategies, enabling richer and more diverse training material. The dataset was built in three stages: a seed version, an intermediate augmented version, and a final version. We benched-marked our dataset with multiple prompting strategies, including zero-shot, few-shot, and augmentation-based approaches, across both vanilla and cooperative multi-agent framework. Our proposed multi-agent framework decomposes the detection process into specialized roles such as self-annotation, span-related feature extraction, demonstration scoring, and final prediction, resulting in a structured and interpretable pipeline for span-level homophobic/transphobic speech detection. Experiments are conducted on both the test split and the combined extended test set, with evaluation using strict token-level, hybrid, and span-overlap metrics to capture both exact and tolerant boundary matches. Our proposed multi-agent framework using augmented V3 data on the combined extended test set, achieved a Macro F1 score of 0.90 , outperforming the strongest single-agent baseline and demonstrating the effectiveness of combining augmentation, multi-agent reasoning, and refined evaluation. Disclaimer: This study includes examples of toxic language strictly for research and educational purposes. The content does not reflect the views of the authors. Reader discretion is advised. GitHub Link: https://github.com/Unit-for-Inclusive-AI/Multi-Agent-HT-Span-Hindi
- 25 February 2026
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 50 (8) , 2414-2439
Fine-Tuning Multilingual BERT for Melancholic Emotion Detection in Kuruntokai
Tamil is one of the world's oldest classical languages still in use. The Tamil language boasts a rich and extensive literary tradition, dating back over 2,000 years. Tamil literature addresses various aspects of life, such as love, war, social values and religion. Tamil classical literature encodes human emotions through dense metaphor, symbolism, and cultural convention, posing significant challenges for automatic emotion analysis. This research investigates the classification of melancholic emotions in Kuruntokai , a Sangam-era Tamil poetic anthology, focusing on two dominant affective categories: Lamentation and Consolation . A manually annotated dataset of 401 poems, along with their explanatory prose ( urai ), is used to evaluate classical machine learning models, recurrent neural networks, and a fine-tuned multilingual BERT (mBERT) model. To address the linguistic complexity of classical Tamil, the framework incorporates morphological analysis, a word reformation algorithm tailored to poetic constructs, and subword-level tokenization. Experimental results show that while Support Vector Machines perform best among classical classifiers, the fine-tuned mBERT model achieves superior performance, attaining an accuracy of 78% on urai-based classification. Quantitative analysis, supported by statistical significance tests and confidence intervals, demonstrates that explanatory prose provides richer emotional cues than the original poems. Qualitative error analysis further reveals how metaphorical compression in poetry leads to misclassification, which is resolved through urai. The findings highlight the effectiveness of transformer-based models for emotion classification in classical Tamil literature and underscore the importance of explanatory prose for reliable affective modelling.
- 25 February 2026
- Published by SAGE Publications in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
- Vol. 50 (8) , 2414-2439
Fine-Tuning Multilingual BERT for Melancholic Emotion Detection in Kuruntokai
Tamil is one of the world's oldest classical languages still in use. The Tamil language boasts a rich and extensive literary tradition, dating back over 2,000 years. Tamil literature addresses various aspects of life, such as love, war, social values and religion. Tamil classical literature encodes human emotions through dense metaphor, symbolism, and cultural convention, posing significant challenges for automatic emotion analysis. This research investigates the classification of melancholic emotions in Kuruntokai , a Sangam-era Tamil poetic anthology, focusing on two dominant affective categories: Lamentation and Consolation . A manually annotated dataset of 401 poems, along with their explanatory prose ( urai ), is used to evaluate classical machine learning models, recurrent neural networks, and a fine-tuned multilingual BERT (mBERT) model. To address the linguistic complexity of classical Tamil, the framework incorporates morphological analysis, a word reformation algorithm tailored to poetic constructs, and subword-level tokenization. Experimental results show that while Support Vector Machines perform best among classical classifiers, the fine-tuned mBERT model achieves superior performance, attaining an accuracy of 78% on urai-based classification. Quantitative analysis, supported by statistical significance tests and confidence intervals, demonstrates that explanatory prose provides richer emotional cues than the original poems. Qualitative error analysis further reveals how metaphorical compression in poetry leads to misclassification, which is resolved through urai. The findings highlight the effectiveness of transformer-based models for emotion classification in classical Tamil literature and underscore the importance of explanatory prose for reliable affective modelling.
- Open Access
- 17 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 17-20
Offensive Language Identification in Code-Mixed Texts: Findings from the DravidianCodeMix Shared Task
- 17 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 17-20
Open AccessOffensive Language Identification in Code-Mixed Texts: Findings from the DravidianCodeMix Shared Task
- Open Access
- 12 August 2025
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 15 (1) , 1-21
Counter-speech generation for homophobic and transphobic social media content in Malayalam
The growing prevalence of hate speech online has amplified acts of discrimination against marginalized populations, with the LGBTQIA+ community being particularly affected. In areas where under-resourced languages such as Malayalam are used, the issue grows more complex because of the absence of localized resources. This research offers an in-depth analysis of the production of counter-speech to address transphobia and homophobia in Malayalam. Our work incorporates both native Malayalam script and Malayalam written in Latin script, addressing the diverse linguistic practices of online users in Kerala. This paper introduces a two-stage pipeline to counter such online abuse. The first stage focuses on dataset creation through a human-in-the-loop process, beginning with 100 seed pairs of hate speech and their corresponding counter-speech manually curated. This set is expanded iteratively using language models culminating in 5,000 validated pairs. In the second stage, we propose a method to generate counter speech in Malayalam that leverages the Retrieval-Augmented Generation framework enhanced by REFINE (Retrieval Evaluation via Fluency, Inversion, and NEarness) for knowledge retrieval and constrained decoding. Evaluation metrics for both dataset quality and model performance demonstrate the effectiveness of this approach in producing diverse, fluent, and target-specific counter-speech. This research provides a foundational resource and scalable strategy for countering hate in low-resource regional languages. GitHub Link: https://github.com/Bharathi-AI-for-Social-Good/CN-Malayalam .
- 12 August 2025
- Published by Springer Nature in Social Network Analysis and Mining
- Vol. 15 (1) , 1-21
Open AccessCounter-speech generation for homophobic and transphobic social media content in Malayalam
The growing prevalence of hate speech online has amplified acts of discrimination against marginalized populations, with the LGBTQIA+ community being particularly affected. In areas where under-resourced languages such as Malayalam are used, the issue grows more complex because of the absence of localized resources. This research offers an in-depth analysis of the production of counter-speech to address transphobia and homophobia in Malayalam. Our work incorporates both native Malayalam script and Malayalam written in Latin script, addressing the diverse linguistic practices of online users in Kerala. This paper introduces a two-stage pipeline to counter such online abuse. The first stage focuses on dataset creation through a human-in-the-loop process, beginning with 100 seed pairs of hate speech and their corresponding counter-speech manually curated. This set is expanded iteratively using language models culminating in 5,000 validated pairs. In the second stage, we propose a method to generate counter speech in Malayalam that leverages the Retrieval-Augmented Generation framework enhanced by REFINE (Retrieval Evaluation via Fluency, Inversion, and NEarness) for knowledge retrieval and constrained decoding. Evaluation metrics for both dataset quality and model performance demonstrate the effectiveness of this approach in producing diverse, fluent, and target-specific counter-speech. This research provides a foundational resource and scalable strategy for countering hate in low-resource regional languages. GitHub Link: https://github.com/Bharathi-AI-for-Social-Good/CN-Malayalam .
- 24 April 2024
- Published by Springer Nature
- p. 443-458
Automatic Identification of Meimayakkam in Tamil Words Using Rule Based and Transfer Learning Approaches
- 24 April 2024
- Published by Springer Nature
- p. 443-458
Automatic Identification of Meimayakkam in Tamil Words Using Rule Based and Transfer Learning Approaches
- 24 April 2024
- Published by Springer Nature
- p. 79-90
The Impact of Tamil Python Programming in Wikisource
- 24 April 2024
- Published by Springer Nature
- p. 79-90
The Impact of Tamil Python Programming in Wikisource
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3075 (1) , 020133
A novel pipeline for privacy-preserving of medical data using federated learning and blockchain
The application of machine learning (ML) in healthcare has the potential to revolutionize the way patients are diagnosed, treated, and monitored. The capability The application of machine learning (ML) in healthcare has the potential to revolutionize the way patients are diagnosed, treated, and monitored. The capability
- 1 January 2024
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 3075 (1) , 020133
A novel pipeline for privacy-preserving of medical data using federated learning and blockchain
The application of machine learning (ML) in healthcare has the potential to revolutionize the way patients are diagnosed, treated, and monitored. The capability The application of machine learning (ML) in healthcare has the potential to revolutionize the way patients are diagnosed, treated, and monitored. The capability
- Open Access
- 15 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 22-24
Findings of Shared task on Sarcasm Identification in Code-Mixed Dravidian Languages
Identifying sarcasm in code-mixed languages presents a pivotal challenge within the domain of natural language processing, given the widespread use of multilingual and multicultural communication on social media platforms. This paper presents findings of the Sarcasm Identification shared task hosted as part of DravidianCodeMix@FIRE-2023. The principal objective of this task was to detect instances of sarcasm within a dataset of code-mixed comments in Tamil-English and Malayalam-English, collected from social media platforms. A total of 11 teams participated in this collaborative effort. This analysis provides a comprehensive assessment of the diverse models employed by the participating teams and the system’s performance was measured in terms of the macro-F1 score.
- 15 December 2023
- Published by Association for Computing Machinery (ACM)
- p. 22-24
Open AccessFindings of Shared task on Sarcasm Identification in Code-Mixed Dravidian Languages
Identifying sarcasm in code-mixed languages presents a pivotal challenge within the domain of natural language processing, given the widespread use of multilingual and multicultural communication on social media platforms. This paper presents findings of the Sarcasm Identification shared task hosted as part of DravidianCodeMix@FIRE-2023. The principal objective of this task was to detect instances of sarcasm within a dataset of code-mixed comments in Tamil-English and Malayalam-English, collected from social media platforms. A total of 11 teams participated in this collaborative effort. This analysis provides a comprehensive assessment of the diverse models employed by the participating teams and the system’s performance was measured in terms of the macro-F1 score.
- Open Access
- 1 August 2023
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 31 (2) , 885-892
Dzongkha to English translation using the neural machine translation approach
In this era of technology, a communication barrier is a thing of the past. With each passing day, different types of language-based applications are being launched. There are 109 official languages Google has translated to date. However, the Dzongkha translation has not been studied. The purpose of this paper was to study Dzongkha to English translation. The parallel corpus was collected from the Dzongkha development commission of Bhutan. The dataset consisted of 53018 sentence pairs. Unique words in Dzongkha and English were 13,393 and 12,506 respectively. Different neural machine translation models were implemented. The experimental results show that the bleu score of Seq2Seq models followed a fluctuating trend. However, the bleu score of the transformer model increases gradually. It was observed that the transformer outperformed the Seq2Seq models. The highest accuracy and the lowest training loss obtained were 84.46% and 0.014858 respectively with a bleu score of 64.89.
- 1 August 2023
- Published by Institute of Advanced Engineering and Science in Indonesian Journal of Electrical Engineering and Computer Science
- Vol. 31 (2) , 885-892
Open AccessDzongkha to English translation using the neural machine translation approach
In this era of technology, a communication barrier is a thing of the past. With each passing day, different types of language-based applications are being launched. There are 109 official languages Google has translated to date. However, the Dzongkha translation has not been studied. The purpose of this paper was to study Dzongkha to English translation. The parallel corpus was collected from the Dzongkha development commission of Bhutan. The dataset consisted of 53018 sentence pairs. Unique words in Dzongkha and English were 13,393 and 12,506 respectively. Different neural machine translation models were implemented. The experimental results show that the bleu score of Seq2Seq models followed a fluctuating trend. However, the bleu score of the transformer model increases gradually. It was observed that the transformer outperformed the Seq2Seq models. The highest accuracy and the lowest training loss obtained were 84.46% and 0.014858 respectively with a bleu score of 64.89.
- 29 May 2023
- Published by Springer Nature
- p. 253-262
Exploring the Opportunities and Challenges in Contributing to Tamil Wikimedia
- 29 May 2023
- Published by Springer Nature
- p. 253-262
Exploring the Opportunities and Challenges in Contributing to Tamil Wikimedia