Divya S

Divya S is a Lecturer in the Department of Computer Science and Engineering, at Shiv Nadar University Chennai. She is working towards submitting her PhD thesis (Anna University). Her research work involves the development of efficient algorithms for Summarization and Sentiment Analysis on Low Resource languages.

She graduated with her B.E in Computer Science and Engineering from Anna University in 2011. She joined her M.E programme at Anna University and graduated in 2013. She has a teaching experience of three years. During her PhD programme, she is a recipient of the Junior Research Fellowship and have also worked as a Teaching Assistant for three years. 

RESEARCH PROFILE:

PUBLICATIONS

• Published a paper entitled “A Transformer Approach for Multi-Document Summarization using TR-BERT” in Indian Journal of Natural Sciences, Vol 14 / ISSUE 78 / JUN 2023.
• Published a book chapter entitled “Hierarchical Text Summarization Using Semantic Similarity” in Research Highlights in Language, Literature and Education Vol. 6, 1-12
• Published a paper entitled “Opinion Classification on Code-mixed Tamil Language” in International Conference on Speech and Language Technologies for Low-resource Languages (pp. 155-168). Cham: Springer International Publishing.
• Published a paper entitled “Unsupervised hierarchical text summarization” in AIP Conference Proceedings (Vol. 2670, No. 1). AIP Publishing.
• Published a paper entitled “Unsupervised Extractive Text Summarization Using Distance-Based Clustering Algorithms” in ICDSMLA 2020: Proceedings of the 2nd International Conference on Data Science, Machine Learning and Applications (pp. 633-640). Springer Singapore.
• Published a paper entitled “Analysis of Audio-Based News Classification Using Machine Learning Techniques” in Mathematical Analysis and Computing: ICMAC 2019, Kalavakkam, India, December 23–24 (pp. 429-441). Springer Singapore.
• Published a paper titled “Transformer Based Model For Offensive Content Recognition In Dravidian Languages” which is selected for presentation in the conference Forum for Information Retrieval Evaluation. http://ceur-ws.org/Vol-3159/T3-7.pdf.
• Published a paper titled “Sentiment Analysis Model For Code-Mixed Tamil Language ” which is selected for presentation in the conference Forum for Information Retrieval Evaluation. http://ceur-ws.org/Vol-3159/T3-7.pdf.

CHALLENGES

• Participated in the “Forum for Information Retrieval Evaluation” – FIRE 2021, for the task “Transformer Based Model for Offensive Language Identification in Dravidian Languages” and is ranked 3rd.
• Participated in the “Forum for Information Retrieval Evaluation” – FIRE 2021, for the task ” sentiment analysis for Dravidian Languages in Code-Mixed Text”.

TASK:

• Offensive and problematic content including insulting, hurtful, derogatory or obscene user contributions are pervasive in social media. HASOC is the task that focusses on developing a model that automates the identification of offensive speech content available online.
• Sentiment analysis is the task of identifying subjective opinions or responses about a given topic. It has been an active area of research in the past two decades in both academia and industry. There is an increasing demand for sentiment analysis on social media texts which are largely code-mixed. Code-mixing is a prevalent phenomenon in a multilingual community where the code-mixed texts are sometimes written in non-native scripts.

GOOGLE SCHOLAR CITATION:

https://scholar.google.com/citations?view_op=list_works&hl=en&user=p3oRqjYAAAAJ