CV
Galway, Ireland · g.negi1@universityofgalway.ie · He/him
LinkedIn · Huggingface · Google Scholar · Github
Research Profile
My research focuses on representing, extracting, and reasoning about opinions in text, specifically on unifying the existing representations with ontology-driven methods. Alongside this, we continue experimenting with scalable, LLM-based annotation alternatives. My broader interests include subjective language understanding, “learning from disagreement” and knowledge-grounded NLP.
Research Experience
Doctoral Researcher, University of Galway Sept 2022 – Present
Thesis: Unified Opinion Representation and Extraction (expected defence: Oct 2026); supervisor: Prof. Paul Buitelaar
Formalised the Unified Opinion Concepts (UOC) ontology, unifying heterogeneous opinion-mining schemas; proposed the UOCE extraction task with an evaluation dataset and tailored metrics.
Built LLM-based annotation and adjudication pipelines for fine-grained opinion analysis; released the resulting models and datasets on HuggingFace.
Developed linguistically enhanced extraction models, and integrated opinion semantics into GNN classifiers for downstream emotion analysis.
Visiting Researcher, University of Oslo Jan 2025 – Feb 2025
Language Technology Group (LTG)
Collaborated on a system for the extraction of narrative roles from text, under the supervision of Prof. Lilja Øvrelid.
Research Assistant, Data Science Institute (DSI), Galway Aug 2021 – Aug 2022
Machine Learning, AI, Natural Language Processing, Semantic Web
PANDEM-2 (EU H2020): suggestion mining, sentiment/emotion analysis, and aspect mining of social media posts, enabling two-way communication between the public and pandemic-management authorities.
Designed, trained, and deployed neural models end-to-end (TensorFlow, TensorFlow Serving, Docker).
Term and taxonomy extraction; corpus collection.
Work Experience
Software Engineer, Centre for Development of Advanced Computing, Pune Sept 2018 – June 2021
Education, Training and Research, Online Examination & Registration Portals
Data processing, consistency checks, and BI dashboards (Grafana, Plotly) for national-scale IAF examination platforms (STAR, AFCAT).
Built an automated help-desk chatbot (RASA) and content-based image-validation services (classification/detection models served as RESTful APIs).
Containerised deployment of applications and models.
Teaching
Teaching Assistant, University of Galway 2022 – 2024
Introduction to NLP (3 semesters)
Advanced Topics in NLP (1 semester)
Academic Service
Shared-Task Co-Organizer, WILDRE-7 Shared Task on Code-Mixed Sentiment Analysis 2024
LREC-COLING 2024 — Configured and managed the CodaLab evaluation platform for task participants.
Education
PhD in Computer Science & Engineering 2022 – present
University of Galway, Ireland (expected defence: Oct 2026)
Post Graduate Diploma in Big Data Analytics 2018
Centre for Development of Advanced Computing (C-DAC), Pune, India
Bachelor of Technology in Electronics and Communication 2013 – 2017
THDC Institute of Hydropower Engineering and Technology, Tehri, India
Technical Skills
Programming Languages: Python, Scala, Java
Data Visualisation: Plotly, Grafana, Matplotlib, Streamlit
Data Engineering: Pandas, Elastic Search (ELK) stack, MongoDB, PostgreSQL
Web Frameworks: Scalatra, Play Framework
Machine Learning/AI Tools: PyTorch, Transformers, HuggingFace, vLLM, DSPy, Weights & Biases, scikit-learn, spaCy, RASA, TensorFlow ecosystem (Keras, TensorBoard, Serving)
Misc.: Docker, GitHub, OpenCV
Publications
Gaurav Negi, Dhairya Dalal, Omnia Zayed, and Paul Buitelaar. 2025. Towards Semantic Integration of Opinions: Unified Opinion Concepts Ontology and Extraction Task. In Proceedings of the 5th Conference on Language, Data and Knowledge, pages 174–185, Naples, Italy. Unior Press.
Dhairya Dalal, Gaurav Negi, and Davide Picca. 2025. LLMs and Emotional Intelligence: Evaluating Emotional Understanding Through Psychometric Tools. In Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization (UMAP ’25). ACM, New York, NY, USA, 323–328.
Gaurav Negi, Atul Kr. Ojha, Omnia Zayed, and Paul Buitelaar. 2025. Towards Temporal Knowledge-Base Creation for Fine-Grained Opinion Analysis with Language Models. In Proceedings of the 3rd Workshop on Knowledge Base Construction from Pre-Trained Language Models (KBC-LM), co-located with ISWC 2025. CEUR-WS Vol. 4041.
Omnia Zayed, Gaurav Negi, Sampritha Hassan Manjunath, Devishree Pillai, and Paul Buitelaar. 2025. LUCE: A Dynamic Framework and Interactive Dashboard for Opinionated Text Analysis. In Proceedings of the 31st International Conference on Computational Linguistics: System Demonstrations, pages 104–116, Abu Dhabi, UAE. ACL.
Egil Rønningstad and Gaurav Negi. 2025. LTG at SemEval-2025 Task 10: Optimizing Context for Classification of Narrative Roles. In Proceedings of SemEval-2025, pages 440–447, Vienna, Austria. ACL.
Gaurav Negi, Rajdeep Sarkar, Omnia Zayed, and Paul Buitelaar. 2024. A Hybrid Approach to Aspect Based Sentiment Analysis Using Transfer Learning. In Proceedings of LREC-COLING 2024, pages 647–658, Torino, Italia. ELRA and ICCL.
Priya Rani, Theodorus Fransen, John P. McCrae, and Gaurav Negi. 2024. MaCmS: Magahi Code-mixed Dataset for Sentiment Analysis. In Proceedings of LREC-COLING 2024, pages 10880–10890, Torino, Italia. ELRA and ICCL.
Priya Rani, Gaurav Negi, Saroj Jha, Shardul Suryawanshi, Atul Kr. Ojha, Paul Buitelaar, and John P. McCrae. 2024. Findings of the WILDRE Shared Task on Code-mixed Less-resourced Sentiment Analysis for Indo-Aryan Languages. In Proceedings of the 7th Workshop on Indian Language Data: Resources and Evaluation, pages 17–23, Torino, Italia. ELRA and ICCL.
Gaurav Negi, Omnia Zayed, Martin Serrano, and Paul Buitelaar. 2026. Semantically Enriching Investor Micro-blogs for Opinion-Aware Emotion Analysis: A Practical Approach. In Proceedings of the SMART AIDA Workshop, co-located with the IEEE International Conference on Smart Computing (SMARTCOMP 2026), Messina, Italy. To appear.
(Pre-print) Gaurav Negi, M. A. Waskow, John P. McCrae, Omnia Zayed, and Paul Buitelaar. 2026. Large Language Models as Automatic Annotators and Annotation Adjudicators for Fine-Grained Opinion Analysis. arXiv preprint arXiv:2601.16800.
Languages
Hindi (Native), English (Full professional proficiency)