Home / Current Issue / Paper 1719159
Stock Market Prediction with Sentiment Analysis
Subject area: Science,Engineering and Technology · Area of research: Stock Market Prediction
DOI: https://doi.org/10.64388/IREV9I12-1719159
Abstract
Stock market prediction is a complex and challenging task due to the volatile and non-linear nature of financial markets. Traditional prediction models mainly rely on historical price data, ignoring the influence of public sentiment and financial news. This research proposes a hybrid model that combines machine learning techniques with sentiment analysis to improve stock price prediction accuracy. Historical stock data and financial news headlines are collected and preprocessed. Sentiment scores are extracted using Natural Language Processing (NLP) techniques and combined with stock market indicators. A Long Short-Term Memory (LSTM) model is implemented for prediction. Experimental results show that integrating sentiment analysis with historical stock data improves prediction accuracy compared to models that rely solely on price data. The proposed system demonstrates the importance of textual information in financial forecasting.
Keywords
Stock Market Prediction, Sentiment Analysis, LSTM, Machine Learning, NLP, Time Series Forecasting
How to cite this paper
@article{1719159,
author = {Jayshree Pansare, Narinder Singh, Vinay Kotwal, Kalhan Koul, Aditya Gundeti},
title = {Stock Market Prediction with Sentiment Analysis},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {12},
pages = {2170-2175},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1719159.pdf},
abstract = {Stock market prediction is a complex and challenging task due to the volatile and non-linear nature of financial markets. Traditional prediction models mainly rely on historical price data, ignoring the influence of public sentiment and financial news. This research proposes a hybrid model that combines machine learning techniques with sentiment analysis to improve stock price prediction accuracy. Historical stock data and financial news headlines are collected and preprocessed. Sentiment scores are extracted using Natural Language Processing (NLP) techniques and combined with stock market indicators. A Long Short-Term Memory (LSTM) model is implemented for prediction. Experimental results show that integrating sentiment analysis with historical stock data improves prediction accuracy compared to models that rely solely on price data. The proposed system demonstrates the importance of textual information in financial forecasting. },
keywords = {Stock Market Prediction, Sentiment Analysis, LSTM, Machine Learning, NLP, Time Series Forecasting},
month = {June},
doi = {https://doi.org/10.64388/IREV9I12-1719159}
}