Scholarlink

This paper presents an innovative approach to stock market prediction by integrating Long Short-Term Memory (LSTM) models with sentiment analysis. Through comprehensive experiments, we explore the efficacy of LSTM models, which are known for capturing long-term dependencies, combined with sentiment analysis for enhanced stock market forecasting. We evaluate how factors like sentiment analysis and technical metrics influence model accuracy across different training epochs. The results indicate that LSTM models integrated with sentiment analysis significantly improve stock market predictions, achieving a peak accuracy of 97% during testing. This research contributes to the domain of market predictions by establishing LSTM models and sentiment analysis as a powerful combination for accurate stock price forecasting.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Forecasting Future Stock Market Values Using Long-Term Memory Models and Sentiment Analysis

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Rohan Jawale,
  • Rushali A. Deshmukh

摘要

This paper presents an innovative approach to stock market prediction by integrating Long Short-Term Memory (LSTM) models with sentiment analysis. Through comprehensive experiments, we explore the efficacy of LSTM models, which are known for capturing long-term dependencies, combined with sentiment analysis for enhanced stock market forecasting. We evaluate how factors like sentiment analysis and technical metrics influence model accuracy across different training epochs. The results indicate that LSTM models integrated with sentiment analysis significantly improve stock market predictions, achieving a peak accuracy of 97% during testing. This research contributes to the domain of market predictions by establishing LSTM models and sentiment analysis as a powerful combination for accurate stock price forecasting.