Di Sha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Di Sha has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Arne Johannssen
Faculty of Business Studies, Harz University of Applied Sciences, 38855 Wernigerode, Germany
3 shared publications - Kim Phuc Tran
University of Lille, ENSAIT, ULR 2461 - GEMTEX - Génie et Matériaux Textiles
3 shared publications Ruolin Wang
2 shared publications- Xianyi Zeng
ENSAIT
2 shared publications Hanhan Wu
1 shared publicationXianyi Zeng
Univ. Lille, ENSAIT ULR 2461—GEMTEX—Génie et Matériaux Textiles Lille France
1 shared publication
Latest Publications
- Open Access
- 10 January 2026
- Published by Elsevier in Energy Reports
- Vol. 15
Carbon price interval prediction by bidirectional long short-term memory and multi-objective optimization with an asymmetric scaling approach
- 10 January 2026
- Published by Elsevier in Energy Reports
- Vol. 15
Open AccessCarbon price interval prediction by bidirectional long short-term memory and multi-objective optimization with an asymmetric scaling approach
- 29 October 2025
- Published by Wiley in Journal of Forecasting
- Vol. 45 (2) , 806-818
A Two‐Stage NLP‐Driven Framework for Interval‐Valued Carbon Price Prediction Using Sentiment Analysis and Error Correction
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.
- 29 October 2025
- Published by Wiley in Journal of Forecasting
- Vol. 45 (2) , 806-818
A Two‐Stage NLP‐Driven Framework for Interval‐Valued Carbon Price Prediction Using Sentiment Analysis and Error Correction
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.