A Comprehensive Review on Sentiment Analysis and Predictive Models for Nifty 50 Market Trends

Author(s)	Mr. Sahal Patel, Dr. Neha Vora
Country	India
Abstract	This study explores a hybrid approach to forecasting the opening direction of the Nifty 50 index by combining financial sentiment analysis and binary logistic regression. Recognizing the growing influence of investor sentiment on market movements, transformer-based language models such as FinBERT and RoBERTa are employed to extract sentiment scores from pre-market financial news and social media sources. These sentiment indicators are then integrated with historical market data to train a logistic regression model that predicts whether the index will open positively or negatively. The model is evaluated on accuracy and precision using recent Nifty 50 data. Results suggest that incorporating sentiment significantly improves predictive performance compared to models relying only on historical price patterns. This research highlights the potential of combining natural language processing with statistical models to improve short-term market forecasting in India.
Keywords	Nifty 50, Stock Market Forecasting, Sentiment Analysis, Logistic Regression, FinBERT, RoBERTa, Natural Language Processing (NLP), Financial Analytics, Investor Sentiment, Machine Learning in Finance
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 6, Issue 5, September-October 2025
Published On	2025-10-13
DOI	https://doi.org/10.63363/aijfr.2025.v06i05.1590
Short DOI	https://doi.org/g97nw5

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research