新冠肺炎疫情阶段特征、公众情绪与农产品价格——基于微博文本挖掘的实证研究

doi:10.16036/j.issn.1000-2650.2021.05.018

摘要/Abstract

摘要： 【目的】新冠肺炎疫情期间,由于封城、交通管制等举措的实施,公众情绪变化剧烈,农产品价格波动明显,因此研究二者之间是否存在关联是一个有趣的议题。【方法】通过微博文本挖掘,分析疫情发展各个阶段公众讨论的主题,并通过情感分析量化公众情绪,进一步构建VAR格兰杰因果关系检验模型研究公众情绪变化与农产品价格波动的关系。【结果】潜伏期和爆发期对新冠病毒有关知识和防控措施的普及较为到位,但在蔓延期仍有谣言不断出现造成恐慌,干扰判断;公众情绪变化不仅是引起猪肉和蔬菜价格变化的格兰杰原因,也是引起牛肉、羊肉和水果价格变化的格兰杰原因;相对于整体情感值,负向情绪数量对农产品价格变化的解释效果更好;对于疫情严重地区,猪肉、牛肉的价格变动领先于公众情绪的变化。【结论】研究结果证实了公众情绪与农产品价格的关联性,为通过引导网络舆情形成健康良好的公众情绪,从而稳定公共卫生事件期间的农产品价格提供了理论参考。

关键词: 新冠肺炎疫情, 农产品价格, 文本挖掘, 情感分析

Abstract: 【Objective】 Due to the closure of the city, traffic control and other measures during the COVID-19 epidemic, the public mood changed dramatically and agricultural prices fluctuated significantly. Therefore, it is an interesting topic to study whether there is a correlation between them.【Method】 Weibo text mining was used to analyze the topics the public discussed at each stage of the epidemic development, and quantified the public sentiment through sentiment analysis to further construct the VAR granger causality test model to study the relationship between public sentiment and agricultural product price fluctuations.【Result】 The knowledge and prevention and control measures of COVID-19 were well popularized in the incubation and outbreak period, but there were still rumors in the spread period, causing panic and interfering with judgment; the change in public sentiment is not only the granger cause of the change in pork and vegetable prices, but also the granger cause of the change in beef, mutton and fruit prices; compared with the overall emotional value, the negative emotional quantity has a better explanation for the change of agricultural product price; for the hardest-hit areas, price changes in pork and beef have outpaced changes in public sentiment. 【Conclusion】 The research results confirmed the correlation between public sentiment and agricultural product prices, providing a theoretical reference for the formation of healthy public sentiment through guiding online public opinion, so as to stabilize agricultural product prices during public health events.

Key words: COVID-19, agricultural product price, text mining, sentiment analysis

中图分类号:

C912.63

邵小彧, 李冬梅, 刘云强. 新冠肺炎疫情阶段特征、公众情绪与农产品价格——基于微博文本挖掘的实证研究[J]. 四川农业大学学报, 2021, 39(5): 688-696.

SHAO Xiaoyu, LI Dongmei, LIU Yunqiang. Characteristics of the COVID-19 Epidemic Stage, Public Sentiment, and Agricultural Product Price: An Empirical Study Based on the Weibo Text Mining[J]. Journal of Sichuan Agricultural University, 2021, 39(5): 688-696.

参考文献

[1] 文军. 新型冠状病毒肺炎疫情的爆发及共同体防控: 基于风险社会学视角的考察[J]. 武汉大学学报(哲学社会科学版), 2020, 73(3): 5-14.
[2] 李谷成. 新冠肺炎疫情对武汉农产品供应链的影响及对策[J]. 华中农业大学学报(社会科学版), 2020(3): 7-13, 168-169.
[3] 李秋萍, 李长健, 肖小勇. 产业链视角下农产品价格溢出效应研究: 基于三元VAR-BEKK-GARCH(1, 1)模型[J]. 财贸经济, 2014(10): 125-136.
[4] 张利庠, 张喜才. 外部冲击对我国农产品价格波动的影响研究: 基于农业产业链视角[J]. 管理世界, 2011(1): 71-81.
[5] 付莲莲, 邓群钊, 翁异静. 国际原油价格波动对国内农产品价格的传导作用量化分析: 基于通径分析[J]. 资源科学, 2014, 36(7): 1418-1424.
[6] 陈宇峰, 薛萧繁, 徐振宇. 国际油价波动对国内农产品价格的冲击传导机制: 基于LSTAR模型[J]. 中国农村经济, 2012(9): 74-87.
[7] 李靓, 穆月英, 赵亮. 国际原油价格、货币政策与农产品价格[J]. 国际金融研究, 2017(3): 87-96.
[8] 王孝松, 谢申祥. 国际农产品价格如何影响了中国农产品价格[J]. 经济研究, 2012, 47(3): 141-153.
[9] 肖皓, 刘姝, 杨翠红. 农产品价格上涨的供给因素分析: 基于成本传导能力的视角[J]. 农业技术经济, 2014(6): 80-91.
[10] 庞贞燕, 刘磊. 期货市场能够稳定农产品价格波动吗: 基于离散小波变换和GARCH模型的实证研究[J]. 金融研究, 2013(11): 126-139.
[11] 陈丹妮. 政策、通胀压力与农产品价格[J]. 中国软科学, 2014(7): 185-192.
[12] 温涛, 王小华. 货币政策对中国农产品价格波动的冲击效应研究[J]. 当代经济科学, 2014, 36(6): 20-29, 122-123.
[13] 苗珊珊. 突发事件信息冲击对猪肉价格波动的影响[J]. 管理评论, 2018, 30(9): 246-255.
[14] 朱信凯, 韩磊, 曾晨晨. 信息与农产品价格波动: 基于EGARCH模型的分析[J]. 管理世界, 2012(11): 57-66, 187-188.
[15] 王天夫, 许弘智. 互联网时代网民职业身份如何影响其政治舆论倾向[J]. 武汉大学学报(哲学社会科学版), 2019, 72(6): 187-196.
[16] 史安斌. 社交媒体时代全球传播的理想模式探究: 基于联合国“微传播”的个案分析[J]. 武汉大学学报(哲学社会科学版), 2018, 71(1): 67-76.
[17] KHATUA A, KHATUA A, CAMBRIA E.A tale of two epidemics: contextual Word2Vec for classifying twitter streams during outbreaks[J]. Information Processing & Management, 2019, 56(1): 247-257.
[18] LAZARD A J, SCHEINFELD E, BERNHARDT J M, et al.Detecting themes of public concern: a text mining analysis of the centers for disease control and prevention's ebola live twitter chat[J]. American Journal of Infection Control, 2015, 43(10): 1109-1111.
[19] GLOWACKI E M, LAZARD A J, WILCOX G B, et al.Identifying the public's concerns and the centers for disease control and prevention's reactions during a health crisis: an analysis of a Zika live Twitter chat[J]. American Journal of Infection Control, 2016, 44(12): 1709-1711.
[20] GRECO F, POLLI A.Emotional text mining: customer profiling in brand management[J]. International Journal of Information Management, 2020, 51: 101934.
[21] ASWANI R, KAR A K, ILAVARASAN P V, et al.Search engine marketing is not all gold: insights from twitter and SEOClerks[J]. International Journal of Information Management, 2018, 38(1): 107-116.
[22] SINGH P, DWIVEDI Y K, KAHLON K S, et al.Can twitter analytics predict election outcome? an insight from 2017 Punjab assembly elections[J]. Government Information Quarterly, 2020, 37(2): 101444.
[23] GROVER P, KAR A K, DWIVEDI Y K, et al.Polarization and acculturation in US election 2016 outcomes-can twitter analytics predict changes in voting preferences[J]. Technological Forecasting and Social Change, 2019, 145: 438-460.
[24] YAQUB U, CHUN S A, ATLURI V, et al.Analysis of political discourse on twitter in the context of the 2016 us presidential elections[J]. Government Information Quarterly, 2017, 34(4): 613-626.
[25] KUŠEN E, STREMBECK M. Politics, sentiments, and misinformation: an analysis of the twitter discussion on the 2016 Austrian Presidential Elections[J]. Online Social Networks and Media, 2018, 5: 37-50.
[26] OLIVEIRA N, CORTEZ P, AREAL N.The impact of microblogging data for stock market prediction: using twitter to predict returns, volatility, trading volume and survey sentiment indices[J]. Expert Systems with Applications, 2017, 73: 125-144.
[27] TETI E, DALLOCCHIO M, ANIASI A.The relationship between twitter and stock prices. Evidence from the US technology industry[J]. Technological Forecasting and Social Change, 2019, 149: 119747.
[28] DAS S, BEHERA R K, KUMAR M, et al.Real-time sentiment analysis of twitter streaming data for stock prediction[J]. Procedia Computer Science, 2018, 132: 956-964.
[29] GROß-KLUßMANN A, KÖNIG S, EBNER M. Buzzwords build momentum: global financial twitter sentiment and the aggregate stock market[J]. Expert Systems with Applications, 2019, 136: 171-186.
[30] NISAR T M, YEUNG M.Twitter as a tool for forecasting stock market movements: a short-window event study[J]. The Journal of Finance and Data Science, 2018, 4(2): 101-119.
[31] 许启发, 伯仲璞, 蒋翠侠. 基于分位数Granger因果的网络情绪与股市收益关系研究[J]. 管理科学, 2017, 30(3): 147-160.
[32] 程萧潇. 场景效应还是内容效应: 财经新闻、网络舆情对股市行情的实证检验[J]. 统计与信息论坛, 2019, 34(7): 69-75.
[33] 部慧, 解峥, 李佳鸿, 等. 基于股评的投资者情绪对股票市场的影响[J]. 管理科学学报, 2018, 21(4): 86-101.
[34] 丁肖丽. 网络讨论、情绪分化与股票市场表现[J]. 湘潭大学学报(哲学社会科学版), 2019, 43(2): 75-81.
[35] 石善冲, 朱颖楠, 赵志刚, 等. 基于微信文本挖掘的投资者情绪与股票市场表现[J]. 系统工程理论与实践, 2018, 38(6): 1404-1412.
[36] BLEI D, NG A, JORDAN M.Latent dirichlet allocation[J]. Journal of Machine Learning Research, 2003, 3: 993-1022.
[37] PANG B, LEE L.Opinion mining and sentiment analysis[J]. Foundations and Trends in Information Retrieval, 2008, 2: 130-135.
[38] GRANGER C.Investigating causal relations by econometric models and cross-spectral methods[J]. Econometrica, 1969, 37: 424-438.
[39] 曾华盛, 苏柳方, 谭砚文. 农产品质量安全媒体负面报道对农产品价格波动的异质性影响[J]. 农业技术经济, 2019(8): 99-114.
[40] 安璐, 吴林. 融合主题与情感特征的突发事件微博舆情演化分析[J]. 图书情报工作, 2017, 61(15): 120-129.
[41] 安璐, 欧孟花. 突发公共卫生事件利益相关者的社会网络情感图谱研究[J]. 图书情报工作, 2017, 61(20): 120-130.
[42] 朱增勇, 浦华, 杨春. 新冠肺炎对生猪产业影响及应对策略[J]. 农业经济问题, 2020(3): 24-30.
[43] 陈菁菁, 黄洁. 疫情事件对农产品市场价格冲击的测度[J]. 统计与决策, 2019, 35(22): 109-112.
[44] LIU Y, ZHU J, SHAO X, et al.Diffusion patterns in disaster-induced internet public opinion: based on a Sina Weibo online discussion about the‘Liangshan fire’ in China[J]. Environmental Hazards, 2021, 20(2): 163-187.
[45] 林燕霞, 谢湘生. 基于社会认同理论的微博群体用户画像[J]. 情报理论与实践, 2018, 41(3): 142-148.
[46] 阳玉堃. 基于文本挖掘的社交网络图书馆公众形象感知研究: 以新浪微博为例[J]. 图书馆论坛, 2019, 39(3): 51-63.