Please wait a minute...
Data Analysis and Knowledge Discovery  2023, Vol. 7 Issue (11): 1-13    DOI: 10.11925/infotech.2096-3467.2022.0928
Current Issue | Archive | Adv Search |
Financial Public Opinion Risk Prediction Model Integrating Knowledge Association and Temporal Transmission
Chen Haoran1,2,Hong Liang1,2()
1School of Information Management, Wuhan University, Wuhan 430072, China
2Big Data Institute, Wuhan University, Wuhan 430072, China
Download: PDF (1240 KB)   HTML ( 41 ) 
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This paper studies financial news representations and the supply chain characteristics of particular companies. Then it utilizes these representations and inter-company associations to improve the prediction of public opinion risks for the target company. [Methods] Firstly, we embedded the company association knowledge into financial news texts based on attention mechanism and Bi-LSTM to learn financial news representation to a specific company. Secondly, we organized the financial news sequence into a news risk transmission network based on inter-company knowledge association. Finally, we used the TGAT layer to model the temporal transmission patterns of risk information through inter-company association and aggregate the risk information to predict the financial public opinion risk of the target company. [Results] The proposed method achieved an accuracy of 0.6246 and an AUC of 0.7021 in the financial public opinion risk prediction task, outperforming the baseline methods. [Limitations] The new model only uses the statistical knowledge associations between stocks of the listed companies and does not incorporate other types of inter-company knowledge associations. [Conclusions] The proposed model can effectively learn risk information relevant to the target company from financial news and the temporal transmission characteristics of public opinion risk in inter-company associations. It demonstrates good financial risk prediction performance.
Key words： Knowledge Association      Text Mining      Financial Risk Prediction      Temporal Graph Neural Networks      Attention Mechanism     
Received: 02 September 2022      Published: 28 March 2023
ZTFLH:  TP391 G353  
Fund:National Natural Science Foundation of China(72074172)
Corresponding Authors: Hong Liang，ORCID：0000-0002-1466-9843，E-mail： hong@whu.edu.cn.   
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Haoran Chen
Liang Hong

Cite this article:

Chen Haoran, Hong Liang. Financial Public Opinion Risk Prediction Model Integrating Knowledge Association and Temporal Transmission. Data Analysis and Knowledge Discovery, 2023, 7(11): 1-13.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2022.0928     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2023/V7/I11/1

Company Relation and Related Stock Trend
Model Framework
Example of Risk Information Transmission Network Construction
Structure of TGAT Layer
对应标签 训练集 验证集 测试集
+CAR_3 48 706 5 174 10 183
-CAR_3 46 178 4 769 9 707
Statistics of News Datasets
模型 Accuracy AUC AP（+） AP（-）
Bi-LSTM 0.585 4 0.624 5 0.598 6 0.572 5
TD-AVG 0.589 4 0.638 4 0.612 9 0.570 3
TD-AGSC 0.594 2 0.640 7 0.609 2 0.580 1
TD-BIEH（Ours） 0.601 9 0.651 4 0.600 0 0.604 4
TD-GCN 0.581 0 0.590 8 0.622 2 0.584 2
TD-Transformer 0.614 7 0.676 5 0.697 4 0.644 6
TD-GraphSAGE 0.616 1 0.680 9 0.696 0 0.643 6
TD-BIEH-T（Ours） 0.624 6 0.702 1 0.737 4 0.681 8
Result of Models on the Test Set
阶段 模型 Accuracy AUC AP（+CAR3） AP（-CAR3）
金融新闻表示 Ours 0.601 9 0.651 4 0.600 0 0.604 4
Ours w/o BERT 0.594 9 0.643 6 0.607 4 0.582 6
Ours w/o industry-BERT 0.597 3 0.648 2 0.589 5 0.609 7
Ours w/o industry-TransH 0.598 1 0.646 5 0.590 9 0.609 2
新闻风险传导 Ours 0.624 6 0.702 1 0.737 4 0.681 8
Ours w/o time-emb 0.623 8 0.677 1 0.711 3 0.631 8
Ours w/o edge-attr 0.602 9 0.690 4 0.730 0 0.668 9
Result of Ablation Experiments
Result of Sensitivity Analysis for Number of TGAT Layers
[1] Hisano R, Sornette D, Mizuno T, et al. High Quality Topic Extraction from Business News Explains Abnormal Financial Market Volatility[J]. PLoS ONE, 2013, 8(6): e64846.
doi: 10.1371/journal.pone.0064846
[2] Atkins A, Niranjan M, Gerding E. Financial News Predicts Stock Market Volatility Better Than Close Price[J]. The Journal of Finance and Data Science, 2018, 4(2): 120-137.
doi: 10.1016/j.jfds.2018.02.002
[3] Chang C Y, Zhang Y, Teng Z, et al. Measuring the Information Content of Financial News[C]// Proceedings of the 26th International Conference on Computational Linguistics:Technical Papers. 2016: 3216-3225.
[4] Loughran T, McDonald B. When is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks[J]. The Journal of Finance, 2011, 66(1): 35-65.
doi: 10.1111/jofi.2011.66.issue-1
[5] Wang C J, Tsai M F, Liu T, et al. Financial Sentiment Analysis for Risk Prediction[C]// Proceedings of the 6th International Joint Conference on Natural Language Processing. 2013: 802-808.
[6] Tsai M F, Wang C J. Financial Keyword Expansion via Continuous Word Vector Representations[C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. 2014: 1453-1458.
[7] 姜富伟, 孟令超, 唐国豪. 媒体文本情绪与股票回报预测[J]. 经济学(季刊), 2021, 21(4): 1323-1344.
[7] (Jiang Fuwei, Meng Lingchao, Tang Guohao. Media Textual Sentiment and Chinese Stock Return Predictability[J]. China Economic Quarterly, 2021, 21(4): 1323-1344.)
[8] So M K P, Mak A S W, Chu A M Y. Assessing Systemic Risk in Financial Markets Using Dynamic Topic Networks[J]. Scientific Reports, 2022, 12(1): Article No. 2668.
[9] Cheng D, Yang F, Wang X, et al. Knowledge Graph-based Event Embedding Framework for Financial Quantitative Investments[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2020: 2221-2230.
[10] Duan J, Zhang Y, Ding X, et al. Learning Target-Specific Representations of Financial News Documents for Cumulative Abnormal Return Prediction[C]// Proceedings of the 27th International Conference on Computational Linguistics. 2018: 2823-2833.
[11] Hu Z, Liu W, Bian J, et al. Listening to Chaotic Whispers: A Deep Learning Framework for News-oriented Stock Trend Prediction[C]// Proceedings of the 11th ACM International Conference on Web Search and Data Mining. 2018: 261-269.
[12] Ding X, Shi J, Duan J, et al. Quantifying the Effects of Long-term News on Stock Markets on the Basis of the Multikernel Hawkes Process[J]. Science China Information Sciences, 2021, 64(9): 192102.
doi: 10.1007/s11432-020-3064-4
[13] Xu W, Liu W, Xu C, et al. REST: Relational Event-driven Stock Trend Forecasting[C]// Proceedings of the Web Conference 2021. 2021: 1-10.
[14] 洪亮, 马费成. 面向大数据管理决策的知识关联分析与知识大图构建[J]. 管理世界, 2022, 38(1):207-219.
[14] (Hong Liang, Ma Feicheng. Knowledge Association Analysis and Big Knowledge Graph Construction for Big Data Management and Decision-making[J]. Journal of Management World, 2022, 38(1):207-219.)
[15] 刘政昊, 钱宇星, 衣天龙, 等. 知识关联视角下金融证券知识图谱构建与相关股票发现[J]. 数据分析与知识发现, 2022, 6(2/3):184-201.
[15] (Liu Zhenghao, Qian Yuxing, Yi Tianlong, et al. Constructing Knowledge Graph for Financial Securities and Discovering Related Stocks with Knowledge Association[J]. Data Analysis and Knowledge Discovery, 2022, 6(2/3):184-201.)
[16] Liang Z, Pan D, Deng Y. Research on the Knowledge Association Reasoning of Financial Reports Based on a Graph Network[J]. Sustainability, 2020, 12(7): 2795.
doi: 10.3390/su12072795
[17] 洪亮, 欧阳晓凤. 金融股权知识大图的知识关联发现与风险分析[J]. 管理科学学报, 2022, 25(4): 44-66.
[17] (Hong Liang, Ouyang Xiaofeng. Knowledge Association Discovery and Risk Analysis Based on Financial Equity Knowledge Graph[J]. Journal of Management Sciences in China, 2022, 25(4): 44-66.)
[18] 唐旭丽, 马费成, 傅维刚, 等. 知识关联视角下的金融知识表示及风险识别[J]. 情报学报, 2019, 38(3):286-298.
[18] (Tang Xuli, Ma Feicheng, Fu Weigang, et al. Research on Financial Knowledge Representation and Risk Identification from Knowledge Connection Perspective[J]. Journal of the China Society for Scientific and Technical Information, 2019, 38(3):286-298.)
[19] Theil C K, Broscheit S, Stuchenschmidt H. PRoFET: Predicting the Risk of Firms from Event Transcripts[C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence. 2020: 5211-5217.
[20] Tsai M F, Wang C J. On the Risk Prediction and Analysis of Soft Information in Finance Reports[J]. European Journal of Operational Research, 2017, 257(1): 243-250.
doi: 10.1016/j.ejor.2016.06.069
[21] Lin T W, Sun R Y, Chang H L, et al. XRR: Explainable Risk Ranking for Financial Reports[C]// Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Springer, Cham, 2021: 253-268.
[22] MacKinlay A C. Event Studies in Economics and Finance[J]. Journal of Economic Literature, 1997, 35(1): 13-39.
[23] Kothari S P, Warner J B. Econometrics of Event Studies[A]//Handbook of Empirical Corporate Finance[M]. Elsevier, 2007: 3-36.
[24] Devlin J, Chang M W, Lee K, et al. BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding[OL]. arXiv Preprint, arXiv:1810.04805.
[25] Huang A H, Wang H, Yang Y. FinBERT: A Large Language Model for Extracting Information from Financial Text[J]. Contemporary Accounting Research, 2022. https://doi.org/10.1111/1911-3846.12832.
[26] 毛瑞彬, 朱菁, 李爱文, 等. 基于自然语言处理的产业链知识图谱构建[J]. 情报学报, 2022, 41(3):287-299.
[26] (Mao Ruibin, Zhu Jing, Li Aiwen, et al. Construction of Knowledge Graph of Industry Chain Based on Natural Language Processing[J]. Journal of the China Society for Scientific and Technical Information, 2022, 41(3):287-299.)
[27] Wang Z, Zhang J, Feng J, et al. Knowledge Graph Embedding by Translating on Hyperplanes[C]// Proceedings of the AAAI Conference on Artificial Intelligence. 2014: 1112-1119.
[28] Xu D, Ruan C, Korgeoglu E, et al. Inductive Representation Learning on Temporal Graphs[C]// Proceedings of International Conference on Learning Representations. 2020.
[29] Kipf T N, Welling M. Semi-supervised Classification with Graph Convolutional Networks[C]// Proceedings of International Conference on Learning Representations. 2017.
[30] Hamilton W L, Ying Z, Leskovec J. Inductive Representation Learning on Large Graphs[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems(NeurIPS). 2017: 1025-1035.
[31] Yun S, Jeong M, Kim R, et al. Graph Transformer Networks[C]// Proceedings of the 33rd International Conference on Neural Information Processing Systems (NeurIPS). 2019: 11983-11993.
[1] He Li, Yang Meihua, Liu Luyao. Detecting Events with SPO Semantic and Syntactic Information[J]. 数据分析与知识发现, 2023, 7(9): 114-124.
[2] Han Pu, Gu Liang, Ye Dongyu, Chen Wenqi. Recognizing Chinese Medical Literature Entities Based on Multi-Task and Transfer Learning[J]. 数据分析与知识发现, 2023, 7(9): 136-145.
[3] Cao Kun, Wu Xinnian, Jin Junbao, Zheng Yurong, Fu Shuang. Identification of Emerging Technology Based on Co-words and Node2Vec Representation Learning[J]. 数据分析与知识发现, 2023, 7(9): 89-99.
[4] Li Jialei, An Peijun, Xiao Xiantao. Review of Methods for Interdisciplinary Topic Identification[J]. 数据分析与知识发现, 2023, 7(4): 1-15.
[5] Lv Qi, Shangguan Yanhong, Zhang Lin, Huang Ying. Interdisciplinary Measurement Based on Automatic Classification of Text Content[J]. 数据分析与知识发现, 2023, 7(4): 56-67.
[6] Han Pu, Zhong Yule, Lu Haojie, Ma Shiwen. Identifying Named Entities of Adverse Drug Reaction with Adversarial Transfer Learning[J]. 数据分析与知识发现, 2023, 7(3): 131-141.
[7] Zhou Ning, Zhong Na, Jin Gaoya, Liu Bin. Chinese Text Sentiment Analysis Based on Dual Channel Attention Network with Hybrid Word Embedding[J]. 数据分析与知识发现, 2023, 7(3): 58-68.
[8] Su Mingxing, Wu Houyue, Li Jian, Huang Ju, Zhang Shunxiang. AEMIA:Extracting Commodity Attributes Based on Multi-level Interactive Attention Mechanism[J]. 数据分析与知识发现, 2023, 7(2): 108-118.
[9] Qiang Zishan,Gu Yijun. Detecting Social Media Rumors Based on Multimodal Heterogeneous Graph[J]. 数据分析与知识发现, 2023, 7(11): 68-78.
[10] Wang jinzheng, Yang Ying, Yu Bengong. Classifying Customer Complaints Based on Multi-head Co-attention Mechanism[J]. 数据分析与知识发现, 2023, 7(1): 128-137.
[11] Peng Cheng, Zhang Chunxia, Zhang Xin, Guo Jingtao, Niu Zhendong. Reasoning Model for Temporal Knowledge Graph Based on Entity Multiple Unit Coding[J]. 数据分析与知识发现, 2023, 7(1): 138-149.
[12] Zhao Ruijie, Tong Xinyu, Liu Xiaohua, Lu Yonghe. Entity Recognition and Labeling for Medical Literature Based on Neural Network[J]. 数据分析与知识发现, 2022, 6(9): 100-112.
[13] Chen Yuanyuan, Ma Jing. Detecting Multimodal Sarcasm Based on SC-Attention Mechanism[J]. 数据分析与知识发现, 2022, 6(9): 40-51.
[14] Tang Jiao, Zhang Lisheng, Sang Chunyan. News Recommendation with Latent Topic Distribution and Long and Short-Term User Representations[J]. 数据分析与知识发现, 2022, 6(9): 52-64.
[15] Zhao Pengwu, Li Zhiyi, Lin Xiaoqi. Identifying Relationship of Chinese Characters with Attention Mechanism and Convolutional Neural Network[J]. 数据分析与知识发现, 2022, 6(8): 41-51.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626，82624938   E-mail:jishu@mail.las.ac.cn