Stock Prediction Using Sentimental Analysis

Read full text Summarise with VIRAT
Cited by: 0
References: 4

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This survey synthesizes findings from recent and influential studies on stock market prediction systems that leverage Sentiment Analysis (SA).Traditional prediction methods, based on technical and fundamental analysis, often fail to account for the crucial role of investor sentiment, which is derived from unstructured text data like news articles and social media.We present a taxonomy that groups the literature based on data sources (e.g., social media, financial news), SA techniques (e.g., lexicon-based, deep learning, Large Language Models), and predictive models (e.g., LSTM, RNN, SVM).Key findings consistently indicate that integrating sentiment features significantly improves predictive accuracy and is essential for modeling complex, non-linear market relationships.The paper concludes by summarizing persistent challenges, including data noise, market nonstationarity, and model interpretability, and proposes promising directions for future research.

Fields of Study & Subjects

Stock Market Forecasting Methods Sentiment Analysis and Opinion Mining Financial Markets and Investment Strategies

Publication details

Journal / source
International Research Journal of Modernization in Engineering Technology and Science
Publication date
30 March 2026
Language
EN