Modeling and Optimization of News-Stock Price Correlation Based on Topic Influence Selection

This study examines the evolving relationship between news topics and stock prices, offering a quantitative analysis of how thematic news coverage influences market volatility. Drawing on a dataset of 90,000 news headlines from the Dow Jones industrial average spanning 2008-2016 and 2018-2023, we classified news into political, technological, entertainment, and other categories, with each theme further divided by sentiment polarity (negative, neutral, and positive). Using Granger causality tests combined with time-period segmentation, we found that certain categories exert significant effects on stock movements within a 1-3 day lag. Specifically, negative entertainment news showed long-term relevance during 2008-2016, while health-related news gained notable importance in 2018-2023, influencing both short- and long-term dynamics; political news likewise revealed strong market-driving potential. To formalize these findings, we introduce a quantitative “topic impact” framework grounded in topic-stock price causality, integrating natural language processing, statistical modeling, and deep learning approaches. Finally, economic validation through backtesting with a multi-factor sentiment strategy demonstrates the framework’s capacity to yield actionable insights for investors.

• Publication year

  2025

• Venue

  IEEE Access

• Publication date

  Unknown publication date

• Fields of study

  Business, Economics, Computer Science

• Identifiers
  DOI 10.1109/ACCESS.2025.3631665
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Hierarchical conv-LSTM and LLM Integrated Model for Holistic Stock Forecasting

  2024cited by this paper
• Forecasting price in a new hybrid neural network model with machine learning

  2024cited by this paper
• Bilingual COVID-19 Fake News Detection Based on LDA Topic Modeling and BERT Transformer

  2023cited by this paper
• Enhancing Cryptocurrency Price Forecasting by Integrating Machine Learning with Social Media and Market Data

  2023cited by this paper
• Unmasking COVID-19 False Information on Twitter: A Topic-Based Approach with BERT

  2023cited by this paper
• Regular Expression Based Medical Text Classification Using Constructive Heuristic Approach

  2019cited by this paper
• News Topic Classification Using Mutual Information and Bayesian Network

  2018cited by this paper
• Stock Market Trend Prediction Using Recurrent Convolutional Neural Networks

  2018cited by this paper
• Deep neural networks, gradient-boosted trees, random forests: Statistical arbitrage on the S&P 500

  2017cited by this paper
• Deep learning for stock market prediction from financial news articles

  2017cited by this paper
• Performance improvement of Support Vector Machine (SVM) With information gain on categorization of Indonesian news documents

  2017cited by this paper
• Towards A Rigorous Science of Interpretable Machine Learning

  2017cited by this paper
• Attention is All you Need

  2017cited by this paper
• A Bayesian regularized artificial neural network for stock market forecasting

  2013cited by this paper
• Baselines and Bigrams: Simple, Good Sentiment and Topic Classification

  2012cited by this paper
• Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm

  2011cited by this paper
• Modern information retrieval: the concepts and technology behind search

  2011cited by this paper
• New Methods of Data Clustering and Classification Based on NMF

  2011cited by this paper
• Twitter mood predicts the stock market

  2010cited by this paper
• Giving Content to Investor Sentiment: The Role of Media in the Stock Market

  2005cited by this paper
• An Extensive Empirical Study of Feature Selection Metrics for Text Classification

  2003cited by this paper
• Expectations and the Effects of Monetary Policy

  2003cited by this paper
• Learning the parts of objects by non-negative matrix factorization

  1999cited by this paper
• Text Categorization with Support Vector Machines: Learning with Many Relevant Features

  1999cited by this paper
• A comparison of event models for naive bayes text classification

  1998cited by this paper
• A Comparative Study on Feature Selection in Text Categorization

  1997cited by this paper

• No citing papers are available for this paper.