融合微博情感分析和深度学习的宏观经济预测方法

doi:10.11772/j.issn.1001-9081.2018041346

计算机应用 ›› 2018, Vol. 38 ›› Issue (11): 3057-3062.DOI: 10.11772/j.issn.1001-9081.2018041346

• 第七届中国数据挖掘会议(CCDM 2018) • 上一篇下一篇

融合微博情感分析和深度学习的宏观经济预测方法

赵军豪¹, 李玉华¹, 霍林², 李瑞轩¹, 辜希武¹

1. 华中科技大学计算机科学与技术学院, 武汉 430074;
2. 广西大学中国-东盟区域发展协同创新中心, 南宁 530004

收稿日期:2018-04-28 修回日期:2018-06-18 出版日期:2018-11-10 发布日期:2018-11-10
通讯作者: 李玉华
作者简介:赵军豪(1994-),男,河南郑州人,硕士研究生,主要研究方向:机器学习、数据挖掘;李玉华(1968-),女,山东禹城人,副教授,博士,CCF高级会员,主要研究方向:数据挖掘、社会网络、机器学习、大数据;霍林(1965-),女,广西柳州人,教授,博士,CCF高级会员,主要研究方向:信息安全、社会网络、大数据;李瑞轩(1974-),男,湖北宜昌人,教授,博士,CCF高级会员,主要研究方向:社会网络、大数据管理、分布式计算、大数据安全;辜希武(1967-),男,湖北武汉人,副教授,博士,主要研究方向:分布式计算、数据挖掘、社会计算、大数据。
基金资助:
国家社会科学基金重大项目（16ZDA0092）；广西高等学校高水平创新团队-数字东盟云大数据安全与挖掘技术创新团队。

Macroeconomic forecasting method fusing Weibo sentiment analysis and deep learning

ZHAO Junhao¹, LI Yuhua¹, HUO Lin², LI Ruixuan¹, GU Xiwu¹

1. College of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan Hubei 430074, China;
2. College of China-ASEAN Collaborative Innovation Center for Regional Development, Guangxi University, Nanning Guangxi 530004, China

Received:2018-04-28 Revised:2018-06-18 Online:2018-11-10 Published:2018-11-10
Supported by:
This work is partially supported by the Major Project of National Social Science Foundation of China (16ZDA0092), the Guangxi High Level Innovation Team in Higher Education Institutions-Innovation Team of ASEAN Digital Cloud Big Data Security and Mining Technology.

摘要/Abstract

摘要： 现代市场经济快速发展的同时也伴随着较高的风险，通过对地区投资情况提前预测，能够提前发现投资风险，为国家、企业的投资决策提供参考。针对宏观经济预测中统计数据滞后和内部关系复杂的问题，提出融合情感分析和深度学习的预测方法（SA-LSTM）。首先考虑微博的强时效性，确定了微博爬取和情感分析的方法，得到微博情感分析的分值，进而结合政府统计的结构化经济指标和长短期记忆神经网络，实现地区投资总额预测。经过实际数据计算验证，在四个数据集上，与不加入微博情感分析的LSTM网络相比，SA-LSTM能够降低预测相对误差4.95，0.92，1.21，0.66个百分点；与差分自回归移动平均模型（ARIMA）、线性回归（LR）、反向传播（BP）神经网络、长短期记忆（LSTM）网络四个方法中的最优方法相比能够降低相对误差0.06，0.92，0.94，0.66个百分点。另外，SA-LSTM在多个时间片上，预测相对误差的方差最小，表明所提方法具有很好的鲁棒性，对数据抖动有良好的适应性。

关键词: 宏观经济, 投资预测, 微博, 情感分析, 深度学习

Abstract: The rapid development of modern market economy is accompanied by higher risks. Forecasting regional investment in advance can find investment risks in advance so as to provide reference for investment decisions of countries and enterprises. Aiming at the lag of statistical data and the complexity of internal relations in macroeconomic forecasting, a prediction method of Long Short-Term Memory based on Weibo Sentiment Analysis (SA-LSTM) was proposed. Firstly, considering the strong timeliness of Weibo texts, a method of Weibo text crawling and sentiment analysis was determined to obtain Weibo text sentiment propensity scores. Then total investment in the region was forecasted by combing with structured economic indicators government statistics and Long Short-Term Memory (LSTM) networks. The experimental results in four actual datasets show that SA-LSTM can reduce the relative error of prediction by 4.95, 0.92, 1.21 and 0.66 percentage points after merging Weibo sentiment analysis. Compared with the best method in the four methods of AutoRegressive Integrated Moving Average model (ARIMA), Linear Regression (LR), Back Propagation Neural Network (BPNN), and LSTM, SA-LSTM can significantly reduce the relative error of prediction by 0.06, 0.92, 0.94 and 0.66 percentage points. In addition, the variance of the prediction relative error is the smallest, indicating that the proposed method has good robustness and good adaptability to data jitter.

Key words: macroeconomy, investment prediction, Weibo, sentiment analysis, deep learning

中图分类号:

TP399

赵军豪, 李玉华, 霍林, 李瑞轩, 辜希武. 融合微博情感分析和深度学习的宏观经济预测方法[J]. 计算机应用, 2018, 38(11): 3057-3062.

ZHAO Junhao, LI Yuhua, HUO Lin, LI Ruixuan, GU Xiwu. Macroeconomic forecasting method fusing Weibo sentiment analysis and deep learning[J]. Journal of Computer Applications, 2018, 38(11): 3057-3062.

参考文献

[1] 郭崇慧,唐焕文. 宏观经济预测模型体系研究[J].运筹与管理, 2001, 10(4):1-8. (GUO C H, TANG H W. Research on macroeconomic forecasting model system[J]. Operations Research and Management Science, 2001, 10(4):1-8.)
[2] 孙安黎, 向春, 伍焓熙. 基于BP神经网络的输电线路工程造价预测模型研究[J]. 现代电子技术, 2018(2):79-82. (SUN A L, XIANG C,WU H X. Study on BP neural network based prediction model for power transmission line project cost[J]. Modern Electronics Technique, 2018(2):79-82.)
[3] 赵海华. 基于灰色RBF神经网络的多因素财政收入预测模型[J]. 统计与决策, 2016(13):79-81.(ZHAO H H. Multi-factor fiscal revenue forecasting model based on grey RBF neural network[J]. Statistics and Decision, 2016(13):79-81.)
[4] AKBILGIC O, BOZDOGAN H, BALABAN M E. A novel hybrid RBF neural networks model as a forecaster[J]. Statistics and Computing, 2014, 24(3):365-375.
[5] 陆泽楠, 商玉林. 基于LSTM神经网络模型的钢铁价格预测[J]. 科技视界, 2017(13):116-117.(CHEN Z N, SHANG Y L. Steel price prediction based on LSTM neural network model[J]. Science and Technology Vision, 2017(13):116-117.)
[6] 李浩, 尤金. 基于深度学习的GDP指标预测分析[J]. 管理工程师, 2017, 22(3):10-12.(LI H, YOU J. Forecasting analysis of GDP index based on deep learning[J]. Management Engineer, 2017, 22(3):10-12.)
[7] FU R, ZHANG Z, LI L. Using LSTM and GRU neural network methods for traffic flow prediction[C]//Proceedings of the 201631st Youth Academic Annual Conference of Chinese Association of Automation. Piscataway, NJ:IEEE, 2017:324-328.
[8] 苏志, 张骐. 基于网络大数据的社会经济预测综述[J]. 情报杂志,2015, 34(7):18-21.(SU Z, ZHANG Q. Researches on socioeconomy forecasting based on internet big data[J]. Journal of Intelligence, 2015,34(7):18-21.)
[9] 陈卫华, 徐国祥. 基于深度学习和股票论坛数据的股市波动率预测精度研究[J]. 管理世界, 2018(1):180-181. (CHEN W H, XU G X. Research on prediction accuracy of stock market volatility based on deep learning and stock forum data[J]. Management World, 2018(1):180-181.)
[10] 刘涛雄,徐晓飞. 互联网搜索行为能帮助我们预测宏观及经济吗?[J].经济研究, 2015(12):68-83. (LIU T X, XU X F. Can internet search behavior help to forecast the macro economy?[J]. Economic Research Journal, 2015(12):68-83.)
[11] HUANG X, ZHANG L, DING Y. The Baidu index:uses in predicting tourism flows - a case study of the forbidden city[J]. Tourism Management, 2016, 58:301-306.
[12] YAO T, ZHANG Y J. Forecasting crude oil prices with the Google index[J]. Energy Procedia, 2017, 105:3772-3776.
[13] 田泽. 建设"丝路经济带"背景下中国对中东国家投资环境评价研究[J]. 现代经济探讨, 2016, 10(1):45-49. (TIAN Z. Research on the evaluation of China's investment environment in middle east countries under the background of building "Silk Road Economic Belt"[J]. Modern Economic Research, 2016, 10(1):45-49.)
[14] 张光建. BP神经网络人口预测模型研究与仿真[J]. 智能计算机与应用, 2016, 6(1):88-90.(ZHANG G J. Research and simulation of population forecasting model of BP neural network[J].Intelligent Computer and Applications,2016,6(1):88-90.)
[15] GRAVES A. Supervised sequence labelling with recurrent neural networks[EB/OL].[2018-03-20]. http://pdfs.semanticscholar.org/a97b/5db17acc731ef67321832dbbaf5766153135.pdf.
[16] SELVIN S, VINAYAKUMAR R, GOPALAKRISHNAN EA, et al. Stock price prediction using LSTM, RNN and CNN-sliding window model[C]//Proceedings of the 2017 International Conference on Advances in Computing, Communications and Informatics. Piscataway, NJ:IEEE, 2017:1643-1647.
[17] GERS F, ECK D. Applying LSTM to time series predictable through time-window approaches[C]//Proceedings of the 2001 International Conference on Artificial Neural Networks. London:Springer-Verlag, 2001:669-676.
[18] LI X, PENG L, HU Y, SHAO J, et al. Deep learning architecture for air quality predictions[J]. Environmental Science & Pollution Research, 2016, 23(22):22408-22417.
[19] HUANG Z, TANG J, XUE S, et al. Speaker adaptation of RNN-BLSTM for speech recognition based on speaker code[C]//Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway, NJ:IEEE, 2016:5305-5309.
[20] 吴玉霞, 温欣. 基于ARIMA模型的短期股票价格预测[J]. 统计与决策, 2016(23):83-86. (WU Y X, WEN X. Short-term stock price forecast based on ARIMA model[J]. Statistics and Decision, 2016(23):83-86.)
[21] 王惠文, 孟洁. 多元线性回归的预测建模方法[J]. 北京航空航天大学学报, 2007, 33(4):500-504. (WANG H W, MENG J. Predictive modeling on multivariate linear regression[J]. Journal of Beijing University of Aeronautics and Astronautics, 2007, 33(4):500-504.)

融合微博情感分析和深度学习的宏观经济预测方法

Macroeconomic forecasting method fusing Weibo sentiment analysis and deep learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[2]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[3]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[4]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[5]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[6]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[7]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[8]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[9]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.
[10]	高钦泉, 黄炳城, 刘文哲, 童同. 基于改进CenterNet的竹条表面缺陷检测方法[J]. 计算机应用, 2021, 41(7): 1933-1938.
[11]	侯笑晗, 金国栋, 谭力宁, 薛远亮. 基于自适应和最优特征的合成孔径雷达舰船检测方法[J]. 计算机应用, 2021, 41(7): 2150-2155.
[12]	李亚芳, 梁烨, 冯韦玮, 祖宝开, 康玉健. 基于社区优化的深度网络嵌入方法[J]. 计算机应用, 2021, 41(7): 1956-1963.
[13]	王月, 江逸茗, 兰巨龙. 基于改进三元组网络和K近邻算法的入侵检测[J]. 计算机应用, 2021, 41(7): 1996-2002.
[14]	杜炎, 吕良福, 焦一辰. 基于模糊推理的模糊原型网络[J]. 计算机应用, 2021, 41(7): 1885-1890.
[15]	刘世泽, 朱奕达, 陈润泽, 罗海勇, 赵方, 孙艺, 王宝会. 基于残差时域注意力神经网络的交通模式识别算法[J]. 计算机应用, 2021, 41(6): 1557-1565.