A Two‐Stage NLP‐Driven Framework for Interval‐Valued Carbon Price Prediction Using Sentiment Analysis and Error Correction
- 29 October 2025
- journal article
- Published by Wiley in Journal of Forecasting
- Vol. 45 (2) , 806-818
Abstract
Accurate predictions of carbon prices are essential for efficient administration and stable operation of carbon markets. Previous studies have mostly focused on point or interval predictions based on point‐valued data. These approaches insufficiently capture the full extent of market volatility. In contrast, interval‐valued data, containing maximum and minimum values, enable more meaningful interval‐valued predictions and thus provide a more comprehensive assessment of uncertainty. However, as previous research in this direction is limited, this study proposes a two‐stage framework for interval‐valued prediction using interval‐valued data. During the initial prediction stage, natural language processing (NLP) techniques are employed to analyze textual data from social media to assess market sentiment. This unstructured data (UD) is then combined with structured data (SD) and fed into a convolutional neural network‐bidirectional long short‐term memory‐Attention (CNN‐BiLSTM‐Attention) mechanism to generate an initial prediction. During the error correction (EC) stage, deviations between the actual and initial predicted values are calculated. These error sequences are then predicted and incorporated into the initial prediction to refine the final results. Trading simulations indicate that the proposed SD‐UD‐CNN‐BiLSTM‐Attention‐EC model can reduce trading risk and improve trading returns.Keywords
This publication has 65 references indexed in Scilit:
- A Multifrequency Data Fusion Deep Learning Model for Carbon Price PredictionJournal of Forecasting, 2024
- Interval Forecasting of Carbon Price With a Novel Hybrid Multiscale Decomposition and Bootstrap ApproachJournal of Forecasting, 2024
- Fortify the investment performance of crude oil market by integrating sentiment analysis and an interval-based trading strategyApplied Energy, 2023
- Forecasting carbon prices based on real-time decomposition and causal temporal convolutional networksApplied Energy, 2022
- An evolutionary cost‐sensitive support vector machine for carbon price trend forecastingJournal of Forecasting, 2022
- Statistical arbitrage trading on the intraday market using the asynchronous advantage actor–critic methodApplied Energy, 2022
- The determinants of CO2 prices in the EU emission trading systemApplied Energy, 2022
- Optimal hybrid framework for carbon price forecasting using time series analysis and least squares support vector machineJournal of Forecasting, 2021
- Forecasting carbon price using a multi‐objective least squares support vector machine with mixture kernelsJournal of Forecasting, 2021
- Carbon Price Forecasting with a Hybrid ARIMA and Least Squares Support Vector Machines Methodology2017