The research on financial systemic risk measurement based on investor sentiment and network text mining focuses on the core value of financial time series prediction in policy formulation, investment decision-making, and risk management. It addresses the challenges posed by its high volatility, multi-scale characteristics, and nonlinear relationships to traditional methods. The research background points out that traditional statistical models such as ARIMA and GARCH are limited by linear assumptions and stationarity requirements, making it difficult to capture the nonlinear dependencies and dynamic factors of multivariate sequences; Although deep learning models such as LSTM and Transformer enhance non-linear processing capabilities, they suffer from black box problems and insufficient interpretability, as well as inadequate utilization of textual information such as investor sentiment. The research method innovatively integrates multi-scale feature extraction (extreme symmetric mode decomposition, ESMD), transfer entropy causal relationship modeling, and graph neural network (GCN). By using transfer entropy to construct causal relationship graphs between variables, interpretability is enhanced. Combining ESMD denoising with FEDformer's long-term prediction ability to strengthen temporal adaptability, risk warning indicators are finally constructed and their application value is verified. Research has shown that the proposed model significantly outperforms five deep models, including LSTNet, MTGNN, and Transformer, in stock price sequence prediction (validated by DM test and RMSE, MAE, and other indicators); Based on the predicted results of stock selection, the mean variance, mean absolute deviation, mean CVaR, and entropy enhanced mean CVaR model are used for portfolio allocation. Under the constraints of prohibiting short selling and transaction costs, the "predicted stock selection+portfolio" hybrid strategy can achieve higher returns. This study integrates investor sentiment text mining and network information to broaden the risk measurement data source, improve model interpretability and temporal adaptability, and provide a scientific framework for accurate measurement of financial systemic risks. Future research can be expanded to non numerical data quantification, cross domain prediction, and multi-objective optimization of investment portfolio construction, further optimizing risk measurement and allocation effects.

Jiahe Sun. Research on Financial Systemic Risk Measurement Based on Investor Sentiment and Network Text Mining. Socio-Economic Statistics Research (2025), Vol. 6, Issue 2: 185-193. https://doi.org/10.38007/SESR.2025.060220.

[1] Chen L. Research on Systemic Financial Risk Measurement and Early Warning Model Based On TVP-SV-VAR Model. Procedia Computer Science, 2025, 262(000):868-877.

[2] Hu Z, Luo K, Liu Y. Classification of motor imagery based on multi-scale feature extraction and fusion-residual temporal convolutional network.  2025.

[3] [Cao B, Jiang X, Leong D, et al. EMD-Fuzzy: An Empirical Mode Decomposition Based Fuzzy Model for Cross-Stimulus Transfer Learning of SSVEP.  2025.

[4] Liu X, Qiu B, Cao J, et al. Freqformer: Image-Demoir\\'eing Transformer via Efficient Frequency Decomposition.  2025.

[5] Liang S, Gu Y. Multi-Modal Dysarthria Severity Assessment Using Dual-Branch Feature Decoupling Network and Mixed Expert Framework. 2024 IEEE 14th International Symposium on Chinese Spoken Language Processing (ISCSLP), 2024:126-130.

[6] Liu, Y. (2025). The Importance of Cross-Departmental Collaboration Driven by Technology in the Compliance of Financial Institutions. Economics and Management Innovation, 2(5), 15-21.

[7] Huang, J. (2025). Research on Resource Prediction and Load Balancing Strategies Based on Big Data in Cloud Computing Platform. Artificial Intelligence and Digital Technology, 2(1), 49-55.

[8] Jiang, Y. (2025). Application and Practice of Machine Learning Infrastructure Optimization in Advertising Systems. Journal of Computer, Signal, and System Research, 2(6), 74-81.

[9] Zou, Y. (2025). Automated Reasoning and Technological Innovation in Cloud Computing Security. Economics and Management Innovation, 2(6), 25-32.

[10] Qi, Y. (2025). Data Consistency and Performance Scalability Design in High-Concurrency Payment Systems. European Journal of AI, Computing & Informatics, 1(3), 39-46.

[11] An, C. (2025). Study on Efficiency Improvement of Data Analysis in Customer Asset Allocatior. Journal of Computer, Signal, and System Research, 2(6), 57-65.

[12] Huang, J. (2025). Optimization and Innovation of AI-Based E-Commerce Platform Recommendation System. Journal of Computer, Signal, and System Research, 2(6), 66-73.

[13] Zhang, X. (2025). Optimization of Financial Fraud Risk Identification System Based on Machine Learning. Journal of Computer, Signal, and System Research, 2(6), 82-89.

[14] Wang, Y. (2025). Exploration and Clinical Practice of the Optimization Path of Sports Rehabilitation Technology. Journal of Medicine and Life Sciences, 1(3), 88-94.

[15] Sheng, C. (2025). Innovative Application and Effect Evaluation of Big Data in Cross-Border Tax Compliance Management. Journal of Computer, Signal, and System Research, 2(6), 40-48.

[16] Sheng, C. (2025). Research on the Application of AI in Enterprise Financial Risk Management and Its Optimization Strategy. Economics and Management Innovation, 2(6), 18-24.

[17] Tu, X. (2025). Optimization Strategy for Personalized Recommendation System Based on Data Analysis. Journal of Computer, Signal, and System Research, 2(6), 32-39.

[18] Zhu, P. (2025). The Role and Mechanism of Deep Statistical Machine Learning In Biological Target Screening and Immune Microenvironment Regulation of Asthma. arXiv preprint arXiv:2511. 05904.

[19] Liu, B. (2025). Design and Implementation of Data Acquisition and Analysis System for Programming Debugging Process Based On VS Code Plug-In. arXiv preprint arXiv:2511. 05825.

[20] Design and Implementation of a Cloud Computing Security Assessment Model Based on Hierarchical Analysis and Fuzzy Comprehensive Evaluation