# Forecasting the Price of Gold with Integrated Media Sentiment—A Prediction Framework Based on Online News Sentiment Mining with CNN-QRLSTM

## TL;DR

This paper introduces a new model for predicting gold prices by combining machine learning with media sentiment analysis from news articles.

## Contribution

The novel CNN-QRLSTM model integrates media sentiment from news with financial data to improve gold price prediction accuracy and quantify uncertainty.

## Key findings

- The CNN-QRLSTM model improves gold price prediction accuracy by incorporating media sentiment.
- Entropy-based methods enhance interpretability of emotion-driven price fluctuations.
- Multi-source data fusion reduces prediction uncertainty and supports quantitative investment strategies.

## Abstract

Accurate gold price forecasting is crucial for economic stability and investment decision-making. In order to improve the accuracy of gold price prediction and quantify the uncertainty of gold price fluctuation, this paper proposes a hybrid model (CNN-QRLSTM) that integrates convolutional neural network (CNN) and quantile regression long- and short-term memory network (QRLSTM) and innovatively introduces news text data to quantify the media sentiment. We combine EEMD with the Hurst index to remove white noise from the original signal, and the processed data is used as the input layer of the prediction model. Furthermore, to demonstrate the impact of news sentiment on gold prices, this paper employs entropy measurement methods based on information theory to quantify the uncertainty and information content embedded within processed gold price sequences and derived sentiment indicators. The mutual information (MI) algorithm, based on information entropy, captures the nonlinear correlations between financial keywords and market sentiment. It constructs a financial sentiment lexicon (covering keywords such as economic policies and geopolitical conflicts), combines semantic rules with context-weighted strategies, calculates sentiment scores for news texts, and generates daily aggregated media sentiment indicators. This entropy-based perception method not only enhances the interpretability of emotion-driven fluctuations but also provides a theoretical foundation for reducing prediction uncertainty through multi-source data fusion. The experiment uses 2022–2025 daily London gold spot price data, Shanghai Gold Exchange gold price data, and the same period of Gold Investment Network gold market news to carry out the study. The empirical study shows that the synergy of multi-source data fusion and the quantile regression mechanism can improve the accuracy of gold price prediction and the new paradigm of risk interpretation while providing theoretical support for the formulation of quantitative investment strategies.