Abstract :

Stock Markets Are Highly Dynamic And Influenced By Multiple Factors Including Economic Indicators, Political Events, And Investor Sentiment. Traditional Stock Prediction Approaches Primarily Rely On Technical And Fundamental Analysis, Often Ignoring Qualitative Sentiment Information Derived From Financial News And Social Media Platforms. This Paper Proposes SPCM (Sentiment Prediction And Classification Model), A Machine Learning-based Stock Recommendation Framework That Integrates Sentiment Analysis With Historical Stock Market Data To Generate Intelligent Investment Recommendations. The System Utilizes Natural Language Processing (NLP) Techniques To Extract Sentiment Polarity From Financial News Articles And Social Media Content. These Sentiment Scores Are Combined With Technical Indicators Such As Moving Average (MA), Relative Strength Index (RSI), And Moving Average Convergence Divergence (MACD) To Construct A Hybrid Feature Set. Supervised Machine Learning Algorithms Including Random Forest, Support Vector Machine (SVM), And Gradient Boosting Are Trained To Classify Stock Actions Into Buy, Hold, Or Sell Categories. Experimental Evaluation Demonstrates That Incorporating Sentiment Features Significantly Improves Prediction Accuracy Compared To Models Based Solely On Historical Price Data. The Proposed SPCM Framework Provides A Reliable Decisionsupport Tool For Investors, Financial Analysts, And Automated Trading Systems By Enabling Data-driven Investment Strategies And Improved Market Forecasting. Keywords— Sentiment Analysis, Stock Market Prediction, Machine Learning, Natural Language Processing, Technical Indicators, Investment Recommendation System.

Published:

06-3-2026

Issue:

Vol. 26 No. 3 (2026)

Page Nos:

37-41

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite