Answers are grounded in this paper and cite their sources.
This paper investigates the relationship between stock market fluctuations and natural language sentiment extracted from social media. Twitter data are analyzed to derive sentiment signals associated with major stocks, which are then aligned with historical price data collected from Yahoo Finance. The study focuses on three main tasks: (i) synchronizing sentiment information with stock price movements, (ii) analyzing the impact of sentiment fluctuations on individual stock volatility, and (iii) forecasting the Vietnamese stock market index (VN-Index) based on sentiment-driven price predictions. Machine learning and deep learning models, including Long Short-Term Memory (LSTM) networks and hybrid architectures such as CNN-BiLSTM with attention mechanisms, are employed to improve temporal variables between sentiment signals and market dynamics. Experimental results on data from 2021 to 2025 demonstrate a noticeable correlation between sentiment scores and stock price movements for companies such as Apple (AAPL) and Amazon (AMZN). The proposed models show competitive performance in predicting future stock trends and VN-Index movements in 2026 and 2027. The obtained results demonstrate that integrating sentiment analysis with time-series modeling provides valuable insights into market volatility and improves predictive accuracy. This work illustrates the potential of natural language-driven approaches as effective tools for stock market analysis and decision support.
No takes yet. Share an insight, caveat, or question.
Tuan et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: