Naman Bhargava

ORCID: 0000-0002-6745-1346
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Computational and Text Analysis Methods
  • Nutritional Studies and Diet
  • Social Acceptance of Renewable Energy
  • Climate Change Communication and Perception
  • Air Quality and Health Impacts
  • Health, Environment, Cognitive Aging
  • Topic Modeling
  • Mathematics Education and Pedagogy
  • Synthetic Aperture Radar (SAR) Applications and Techniques
  • Remote Sensing in Agriculture
  • Risk Perception and Management
  • Knowledge Management and Technology
  • Mathematics Education and Teaching Techniques
  • Soil Moisture and Remote Sensing
  • Cognitive and developmental aspects of mathematical skills

University of Michigan
2024

PSG INSTITUTE OF TECHNOLOGY AND APPLIED RESEARCH
2022-2024

Thapar Institute of Engineering & Technology
2024

This study utilized large language models (LLMs) to analyze public sentiment in the United States (US) regarding nuclear power on social media, focusing X/Twitter, considering climate change challenges and advancements technology. Approximately, 1.26 million tweets from 2008–2023 were examined fine-tune LLMs for classification. We found crucial role of accurate data labeling model performance, with potential implications a 15% improvement, achieved through high-confidence labels....

10.1016/j.rser.2024.114570 article EN cc-by-nc Renewable and Sustainable Energy Reviews 2024-06-01

In this work, we propose and assess the potential of generative artificial intelligence (AI) as a tool for facilitating public engagement around clean energy sources. Such an application could increase literacy—an awareness low-carbon sources among therefore leading to increased participation in decision-making about future systems. We explore use AI communicate technical information general public, specifically realm nuclear energy. explored 20 AI-powered text-to-image generators compared...

10.1038/s41598-024-79705-4 article EN cc-by-nc-nd Scientific Reports 2024-12-05

Breast milk serves as a vital source of essential nutrients for infants. However, human contamination via the transfer environmental chemicals from maternal exposome is significant concern infant health. The to plasma concentration (M/P) ratio critical metric that quantifies extent which these into breast milk, impacting exposure. Machine learning-based predictive toxicology models can be valuable in predicting with high propensity milk. To this end, we build such classification- and...

10.1021/acsomega.3c09392 article EN cc-by-nc-nd ACS Omega 2024-03-06

Abstract Breast milk serves as a vital source of essential nutrients for infants. However, human contamination via transfer environmental chemicals from maternal exposome is significant concern infant health. Machine learning based predictive toxicology models can be valuable in predicting with high propensity to into milk. To this end, we build such classification- and regression-based by employing multiple machine algorithms leveraging the largest curated dataset date 375 known Milk Plasma...

10.1101/2023.08.06.552173 preprint EN bioRxiv (Cold Spring Harbor Laboratory) 2023-08-07

In this work, we propose and assess the potential of generative artificial intelligence (AI) to generate public engagement around clean energy sources. Such an application could increase literacy -- awareness low-carbon sources among therefore leading increased participation in decision-making about future systems. We explore use AI communicate technical information general public, specifically realm nuclear energy. explored 20 AI-powered text-to-image generators compared their individual...

10.2139/ssrn.4719047 preprint EN 2024-01-01

This study utilized large language models (LLMs) to analyze public sentiment in the United States (US) regarding nuclear power on social media, focusing X/Twitter, considering climate change challenges and advancements technology. Approximately, 1.26 million tweets from 2008-2023 were examined fine-tune LLMs for classification. We found crucial role of accurate data labeling model performance, with potential implications a 15\% improvement achieved through high-confidence labels....

10.2139/ssrn.4763795 preprint EN 2024-01-01

In this work, we propose and assess the potential of generative artificial intelligence (AI) to generate public engagement around clean energy sources. Such an application could increase literacy -- awareness low-carbon sources among therefore leading increased participation in decision-making about future systems. We explore use AI communicate technical information general public, specifically realm nuclear energy. explored 20 AI-powered text-to-image generators compared their individual...

10.48550/arxiv.2312.01180 preprint EN cc-by arXiv (Cornell University) 2023-01-01
Coming Soon ...