Faculty at School of Engineering

Sonia Khetarpaul

Sonia Khetarpaul

Associate Professor

School of Engineering


Contact Information

Dr. Sonia Khetarpaul is an Associate Professor in the Department of Computer Science and Engineering at Shiv Nadar Institution of Eminence. She earned her Ph.D. in Computer Science from IIT Delhi and has built a distinguished academic career spanning data science, spatio-temporal data mining, natural language processing, information retrieval, and large language models.

Her research lies at the intersection of Data Science, Artificial Intelligence, and Human-Centered Computing, with applications in smart transportation, mobility analytics, education, healthcare, and legal technologies. Her recent work focuses on LLMs, Retrieval-Augmented Generation (RAG), and domain-adaptive AI, emphasizing scalable, explainable, and socially beneficial solutions.

She is the recipient of the prestigious IBM Ph.D. Fellowship and has published in leading international journals and conferences. She is currently serving as Principal Investigator on a Council of Science & Technology, Uttar Pradesh (CSTUP) funded project, “Voice-based AI Healthcare Assistant: Automating Forms, Inquiries, and Initial Diagnosis,” a two-year project focused on healthcare, natural language processing, and automatic speech recognition. The project aims to develop voice-based AI solutions that can simplify healthcare interactions and support preliminary diagnosis.

Further details about my work can be accessed at the following web links:

Data Science, Natural Language Processing, Spatio-temporal Data Mining, Information Retrieval, and Large Language Models

  • Doctor of Philosophy (PhD) in Computer Science from Indian Institute of Technology, Delhi (2016)
    • Thesis Advisor: Prof. S. K. Gupta (IITD), Dr. L. Venkat Subramaniam (IBM Research, India)
    • Thesis Title: Analyzing Moving Objects Data in Spatio-Temporal Space and Social Networks
  • Master of Technology in Information Technology, Guru Gobind Singh Indraprastha University, Delhi (2004)

  • Associate Professor, Shiv Nadar Institution of Eminence, Delhi NCR: Jan 2023 – Present
  • Undergraduate Advisor (CSE): Jan 2019 – Dec 2023
  • Assistant Professor, Shiv Nadar Institution of Eminence, Delhi NCR: Jul 2017 – Dec 2022
  • Teaching Assistant, Indian Institute of Technology Delhi, Delhi NCR: Jan 2010 – Dec 2015
  • Assistant Professor, Northern India Engineering College, Delhi: Jul 2004 – Dec 2009

  • IBM Ph.D. Fellowship, 2012.
  • SNU Excellence in Undergraduate Advising Award, 2021.

IEEE Member, ACM, ACM-W

Journals:

  1. Kapil Vuthoo, Khetarpaul, S., Subramaniam L.V. Datasets, Models and NLP Techniques for Legal Contracts–A Survey. Expert Systems, Wiley, 43, no. 6: e70267, 2026.
  2. Tejansh Sachdeva, Mitaali Singhal, Khetarpaul, S. Promoting Fairness in LLMs: Detection and Mitigation of Gender Bias. Knowledge and Information Systems, Springer, 68, 107 (2026), 2026.
  3. Bhatia, M., and Khetarpaul, S. AI-enhanced bilingual banking assistant. Scientific Reports, Springer 15.1 (2025): 37526.
  4. Mishra, S., Khetarpaul, S. Identifying and recommending taxi hotspots in spatio-temporal space. GeoInformatica, Springer, Volume 29, pages 93–113 (2025), 2025.
  5. Mishra, S., Khetarpaul, S. uR-tree: A spatial index structure for handling multiple point selection queries. Multimedia Tools and Applications, Springer, Volume 82, pages 8093–8111, 2023.
  6. Khetarpaul, S. Mining location-based social networks to understand citizen check-in patterns. Computing, Springer, Volume 103, pages 2967–2993, 2021.
  7. Singh, R.K., Khetarpaul, S., et al. SHEG: Summarization and headline generation of news articles. Neural Computing and Applications, Springer, Volume 103, pages 2967–2993, 2021.
  8. Khetarpaul, S., Gupta S.K., Subramaniam, L.V. Mining optimal meeting points for moving users. Social Network Analysis and Mining, Springer, Volume 8, article number 50, 2018.
  9. Khetarpaul, S., Gupta S.K., Subramaniam L.V. Spatiotemporal social (STS) data model: correlating social networks and spatiotemporal data. Social Network Analysis and Mining, Springer, Volume 6, article number 81, 2016.

Selected Refereed Conference Publications:

  1. Swaroop, Anvitha; Prasad, Kritika; Khetarpaul, Sonia; SiteSense: Optimizing Restaurant Site Selection Using a Comprehensive Big Data and Artificial Intelligence: 13th International Conference on Big Data Analytics, BDA 2025, Springer.
  2. Badoni, Aayush; Singh, Divyansh Anand; Vuthoo, Kapil; Singh, Shivansh; Khetarpaul, Sonia; Subramaniam, L Venkata; IndLaw-QA: Fine-Tuned LLMs with RAG for Indian Legal QA. 13th International Conference on Big Data Analytics, BDA 2025, Springer.
  3. Khetarpaul, Sonia; Sharan, P Y; Traffic-Aware Optimal Taxi Placement Using Graph Neural Network-Based Reinforcement Learning, 19th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2025, IEEE.
  4. Srivastava, Saksham; Singh, Pooja; Khetarpaul, Sonia; Sharma, Unnat; Investigating Cultural Bias: A Comparative Study of Large Language Models, 11th International Conference on Pattern Recognition and Machine Intelligence, PReMI 2025.
  5. Khetarpaul, Sonia; Baazaoui-Zghal, Hajer; Gupta, Shreya; Bist, Vidushi; Bhatnagar, Devina; A Comparative Study of AI-Driven Ontology Enrichment for Environmental Sustainability. 13th IEEE International Conference on Big Data, IEEE BigData 2025.
  6. Pattnayak, Aryaman; Ramkumar, Adhityanarayan; Khetarpaul, Sonia; Vuthoo, Kapil; LawMate: Leveraging Domain-Specific LLMs for the Indian Legal Ecosystem. Asian Conference on Intelligent Information and Database Systems, ACIIDS 2025, Springer.
  7. Khetarpaul, Sonia; Patil, Vedanta Vivek; Sura, Mitra Abhi; Sharma, Shrey; Singh, Pooja; CLOR-QA: Cross-Lingual Open-Retrieval Question Answering Model with Dynamic Database Integration. International Conference on Information Integration and Web Intelligence, iiWAS 2024, Springer Nature.
  8. Sharma, Dolly; Khetarpaul, Sonia; Verma, Chinmayi; Jain, Prateek; Combining GraphSAGE and Label Propagation for Node Classification in Graphs. International Conference on Information Integration and Web Intelligence, iiWAS 2024, Springer.
  9. Khetarpaul, Sonia; Sharma, Dolly; Sinha, Shreya; Nagpal, Aryan; Narang, Aarush; Analyzing the Efficacy of Large Language Models: A Comparative Study. International Conference on Database and Expert Systems Applications, DEXA 2024, Springer Nature.
  10. Sonia Khetarpaul, Lakshay Jain, Kush Goyal, and P. Vishnu Tej. Lecture Video Summarization using Deep Learning. 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Springer.
  11. Ila Ananta, Sonia Khetarpaul, and Dolly Sharma. Symptoms–Disease Detecting Conversation Agent using Knowledge Graphs. ACSW, ACM, 2024.
  12. Sonia Khetarpaul, Dolly Sharma, Somya Ranjan Padhi, and Saurabh Mishra. Enhancing Taxi Placement in Urban Areas Using Dominating Set Algorithm with Node and Edge Weights. International Conference of Information Integration and Web Intelligence iiWAS 2023, Springer, 2023.

Invited Talks and Academic Outreach

  • Invited talk on LLMs in Education, DPS, Gurugram, 2025.
  • Guest lecture on Machine Learning for Location-Based Systems, 2020.
  • Invited talk on Spatio-Temporal Data Mining and Urban Analytics, NSUT, Delhi, 2017.

Conference Presentations:

  • “Traffic-Aware Optimal Taxi Placement Using Graph Neural Network-Based Reinforcement Learning”, 19th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2025, Delhi, India, IEEE.
  • “Lecture Video Summarization using Deep Learning”, 16th Asian Conference on Intelligent Information and Database Systems, ACIIDS 2024, Dubai, Springer.
  • “Enhancing Taxi Placement in Urban Areas Using Dominating Set Algorithm with Node and Edge Weights”. International Conference of Information Integration and Web Intelligence, iiWAS 2023, Bali, Indonesia, Springer, 2023.
  • “Correlating Social Interconnections of Users with Spatio-Temporal Check-ins Behavior.” International Workshop on Spatial and Spatiotemporal Data Mining (SSTDM), IEEE ICDM, Barcelona, Spain, 2016.
  • “Mining GPS data to determine interesting locations”. In Proceedings of the 8th International Workshop on Information Integration on the Web: in conjunction with WWW 2011 (IIWeb '11), Bangalore, India, Association for Computing Machinery.

Undergoing Project Grant:

Title of the Project: Voice-based AI Healthcare Assistant: Automating Forms, Inquiries, and Initial Diagnosis

Scope: Healthcare, Natural Language Processing, Automatic Speech Recognition

Funding Agency: Council of Science & Technology, Uttar Pradesh, 2025 (Duration: 2 years)

Investigators: Dr. Sonia Khetarpaul (PI), Dr. Suchi Kumari, Prof. Rajib Mall

  • Data Mining and Knowledge Discovery, Springer
  • Scientific Reports, Springer
  • Artificial Intelligence and Law, Springer
  • Journal of Transport Policy, Elsevier
  • Neural Processing Letters, Springer
  • Discover Networks, Springer
  • Applied Network Science, Springer
  • Journal of Transport Geography, Elsevier