基于机器学习算法和社会网络分析方法的议程设置验证——以新冠疫情初期的“中国援助”为例
Verification on Agenda Setting Based on Machine Learning Algorithms and Social Network Analysis Methods—A Case Study of “Chinese Assistance” in the Early Stage of COVID-19
摘要: 本文通过使用机器学习算法和社会网络分析方法，以新冠疫情初期的“中国援助”为例验证了议程设置的三个层次。首先，通过2020年3月1日~2020年4月30日的媒体报道量和百度指数，初步分析媒体报道量与公众关注程度的简单相关关系，得到两个结论：一是公众关于“中国援助”的关注度与媒体的报道量高度相关；二是当代媒介环境下，媒体影响公众的最佳时滞期由7天缩短到了当天。其次，采用支持向量机分类方法，将每篇媒体新闻报道与群众评论所蕴含的思想态度分成积极正向和消极负向两方面，进而分析媒体新闻报道对群众评论的主观思想的影响，通过分析认为媒体对疫情下“中国援助”偏向积极地报道带动了公众偏向积极地看待中国援助国外。最后, 通过TextRank算法和社会网络分析方法，构建媒体属性矩阵和公众属性矩阵，并分析媒体报道和公众评论的相关性，发现媒体的报道推动了公众对“中国援助”事件的认知网络的构建。
Abstract: Machine learning algorithms and social network Analysis methods are used to verify the three levels of agenda setting in the early stage of “Chinese assistance” in COVID-19. Firstly, through the media coverage and Baidu Index from March 1, 2020 to April 30, 2020, this paper preliminarily analyzes the simple correlation between media coverage and public attention, and two conclusions are obtained: the public’s attention to “Chinese assistance” is highly related to the amount of media coverage, thus the first level of agenda setting is verified; in the contemporary media environment, the best time lag period for media to affect the public has been shortened from 7 days to the same day. Secondly, by using SVM model, the thoughts and attitudes contained in each media news report and public comments are divided into positive and negative aspects, and then the impact of media coverage on the subjective thoughts of public comments is analyzed. Through the analysis, it is considered that the positive media coverage of “Chinese assistance” has led the public to view Chinese assistance to foreign countries positively, thus the second level of agenda setting is verified. Finally, through TextRank algorithm and social network analysis methods, the media attribute matrix and public attribute matrix are constructed, and the correlation between media coverage and public comments is analyzed. It is concluded that media coverage affects the public’s cognitive network construction about the “Chinese assistance” event, thus the third level of agenda setting is verified.
文章引用：万鑫, 唐润发, 熊令纯, 李裕梅. 基于机器学习算法和社会网络分析方法的议程设置验证——以新冠疫情初期的“中国援助”为例[J]. 数据挖掘, 2022, 12(4): 368-380. https://doi.org/10.12677/HJDM.2022.124034

参考文献

[1] 陈贵梧. “无组织的有序”: 社会化媒体何以影响议程的设置?——以滴滴顺风车安全事件为例[J]. 电子政务, 2021(9): 2-12.
[2] 李青青. 新媒体时代媒介议程设置理论嬗变与发展[J]. 中国出版, 2021(16): 28-31.
[3] Neuman, W.R., Guggenheim, L., Jang, S.M. and Bae, S.Y. (2014) The Dynamics of Public Attention: Agenda-Setting Theory Meets Big Data. Journal of Communication, 64, 193-214. [Google Scholar] [CrossRef] 
[4] Wanta, W., Golan, G. and Lee, C. (2004) Agenda Setting and Internation-al News: Media Influence on Public Perceptions of Foreign Nations. Journalism & Mass Communication Quarterly, 81, 364-377. [Google Scholar] [CrossRef] 
[5] 杨立公, 朱俭, 汤世平. 文本情感分析综述[J]. 计算机应用, 2013, 33(6): 1574-1578+1607.
[6] 吴杰胜, 陆奎. 基于多部情感词典和规则集的中文微博情感分析研究[J]. 计算机应用与软件, 2019, 36(9): 93-99.
[7] 王晗啸, 李成名, 于德山, 巴志超. 基于上下文语义的网络议程设置研究——以红黄蓝事件为例[J]. 国际新闻界, 2020, 42(4): 77-97.
[8] Pang, B., Lee, L. and Vaithyanathan, S. (2002) Thumbs up? Sentiment Classification using Machine Learning Techniques. Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing, Vol. 10, 79-86. [Google Scholar] [CrossRef] 
[9] 林聚任. 社会网络分析: 理论、方法与应用[M]. 北京: 北京师范大学出版社, 2009.
[10] 郝帅, 罗晨. 第三层次议程设置检验——“李文星事件”中的媒体与公众议程网络分析[J]. 教育传媒研究, 2019, 19(2): 61-69.
[11] Tomas, M., Chen, K., Corrado, G. and Dean, J. (2013) Efficient Estima-tion of Word Representations in Vector Space. Computation and Language, arXiv: 1301.3781.
[12] Cortes, C. and Vap-nik, V. (1995) Support-Vector Networks. Machine Learning, 20, 273-297. [Google Scholar] [CrossRef] 
[13] Mountrakis, G., Im, J. and Ogole, C. (2011) Support Vector Machines in Remote Sensing: A Review. ISPRS Journal of Photogrammetry and Remote Sensing, 66, 247-259. [Google Scholar] [CrossRef] 
[14] Schuldt, C., Laptev, I. and Caputo, B. (2004) Recognizing Human Actions: A Local SVM Approach. International Conference on Pattern Recognition, Cambridge, 26 August 2004, 32-36. [Google Scholar] [CrossRef] 
[15] Mihalcea, R. and Tarau, P. (2004) TextRank: Bringing Order into Texts. Proceedings of 2004 Conference on Empirical Methods in Natural Language Processing, Barcelona, 25-26 July 2004, 404-411.
[16] 王运锋, 夏德宏, 颜尧妹. 社会网络分析与可视化工具NetDraw的应用案例分析[J]. 现代教育技术, 2008, 18(4): 85-89.
[17] Creswick, N. and Westbrook, J.I. (2010) Social Network Analysis of Medication Advice-Seeking Interactions among Staff in an Australian Hospital. International Journal of Medical Informatics, 79, e116-e125. [Google Scholar] [CrossRef] [PubMed]
[18] 刘军. QAP: 测量“关系”之间关系的一种方法[J]. 社会, 2007, 27(4):164-174.
[19] 窦慧彬. 我国传统媒体与社交媒体关于“二孩”政策的议程影响研究[D]: [硕士学位论文]. 上海: 上海外国语大学, 2017.
[20] Roberts, M., Wanta, W. and Dzwo, T.H. (2002) Agenda Setting and Issue Salience Online. Communication Research, 29, 452-465. [Google Scholar] [CrossRef] 
[21] Kim, C. and Klabjan, D. (2020) A Simple and Fast Algorithm for L1-Norm Kernel PCA. IEEE Transactions on Pattern Anal-ysis & Machine Intelligence, 42, 1842-1855. [Google Scholar] [CrossRef] 
[22] Kweon, S.H., Go, T., Kang, B.Y., Cha, M.-K., Kim, S.-J., Kweon, H.-J., et al. (2019) Study on Agenda-Setting Structure between SNS and News: Focusing on Application of Network Agenda-Setting. International Journal of Contents, 15, 10-24. [Google Scholar] [CrossRef] 

为你推荐