Please wait a minute...
Advanced Search
数据分析与知识发现  2022, Vol. 6 Issue (1): 69-79     https://doi.org/10.11925/infotech.2096-3467.2021.0407
     研究论文 本期目录 | 过刊浏览 | 高级检索 |
基于网络分析和文本挖掘的意见领袖影响力研究*
孙羽,裘江南()
大连理工大学经济管理学院 大连 116000
Studying Opinion Leaders with Network Analysis and Text Mining
Sun Yu,Qiu Jiangnan()
School of Economics and Management, Dalian University of Technology, Dalian 116000, China
全文: PDF (1577 KB)   HTML ( 46
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】 研究意见领袖类别划分方法,从多角度对不同类别意见领袖特点做出评价。【方法】 提出利用社团划分识别意见领袖类别的方法,并利用二维分析框架模型从网络扩散能力和文本情绪支配度两维度综合分析意见领袖影响力。实证分析选取推特数据,通过网络分析和文本挖掘对不同类别意见领袖进行对比。【结果】 意见领袖被识别为三类社团,在网络扩散能力和情绪支配度两维度呈现不同排名,且两维度相关系数的绝对值小于0.3,不具备相关性,二维矩阵分析相较传统加权求和的方法能更全面地反映影响力特点。【局限】 在文本情绪影响力评价中,只对原文的文本进行分析,后续研究可结合评论内容对意见领袖做出进一步评价。【结论】 本文方法有助于分析不同类别意见领袖影响公众的程度和特点,帮助管理者有针对性地挖掘各类意见领袖的舆论引导价值,引导风险事件中的舆论导向。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
孙羽
裘江南
关键词 社团划分意见领袖社交网络二维分析框架情感分析    
Abstract

[Objective] This paper tries to study the classification scheme for opinion leaders and evaluate their characteristics from multiple perspectives. [Methods] We proposed a method to classify opinion leaders by community division. Then, we comprehensively analyzed their influences from the dimensions of network diffusion ability and emotional dominance. We conducted an empirical analysis with Twitter data, and compared the influence of different types of opinion leaders through network analysis and text mining. [Results] Opinion leaders are identified as three communities, which rank differently in network diffusion ability and emotional dominance. The two dimensions show no correlation with an absolute value of correlation coefficient less than 0.3. Compared with the traditional weighted summing method, the two-dimensional matrix analysis can reflect the influence characteristics more comprehensively. [Limitations] In the evaluation of emotional influence, we only analyzed the original texts, and future studies will include the comments. [Conclusions] The proposed methods could analyze the degrees and characteristics of the opinion leaders' influence. It helps us understand all kinds of opinion leaders and guide the public opinion directions more effectively in risk management.

Key wordsCommunity Division    Opinion Leader    Social Network    Two-Dimensional Analytical Framework    Sentiment Analysis
收稿日期: 2021-04-26      出版日期: 2022-02-22
ZTFLH:  TP393  
基金资助:*本文系辽宁省社会科学规划基金项目的研究成果之一(L19BGL001)
通讯作者: 裘江南,ORCID:0000-0001-5320-8479     E-mail: qiujiangnan@gmail.com
引用本文:   
孙羽, 裘江南. 基于网络分析和文本挖掘的意见领袖影响力研究*[J]. 数据分析与知识发现, 2022, 6(1): 69-79.
Sun Yu, Qiu Jiangnan. Studying Opinion Leaders with Network Analysis and Text Mining. Data Analysis and Knowledge Discovery, 2022, 6(1): 69-79.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2021.0407      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2022/V6/I1/69
Fig.1  Louvain算法
Fig.2  社团划分过程
Fig.3  主观划分与社团划分对应结果
指标 社团1 社团2 社团3
入度中心性 0.159 0.248 0.214
入接近中心性 0.337 0.389 0.373
中介中心性 0.028 0.026 0.020
PageRank 0.034 0.014 0.014
综合得分 0.113 0.138 0.120
Table 1  各社团网络节点重要性均值
Fig.4  重要性指标累计分布函数
Fig.5  社团划分网络
主成分 方差贡献率/% 累计贡献率/%
1 39.296 39.296
2 33.139 72.434
3 18.395 90.830
4 9.170 100.000
Table 2  总方差解释
主成分 影响力参数 真实性参数 代词参数 从属参数
1 0.704 -0.195 0.283 0.622
2 -0.128 0.741 0.654 0.079
3 -0.237 0.405 -0.585 0.662
Table 3  主成分系数矩阵
Fig.6  各社团情绪分析
Fig.7  二维框架分析
[1] Chang S P. Does Twitter Motivate Involvement in Politics? Tweeting, Opinion Leadership, and Political Engagement[J]. Computers in Human Behavior, 2013, 29(4):1641-1648.
doi: 10.1016/j.chb.2013.01.044
[2] 刘柳青. 微博意见领袖舆论引导及其策略探讨[J]. 新媒体研究, 2020, 6(8):13-16, 23.
[2] ( Liu Liuqing. Discussion on Public Opinion Guidance and Strategy of Microblog Opinion Leaders[J]. New Media Research, 2020, 6(8):13-16, 23.)
[3] 王林, 王可, 吴江. 社交媒体中突发公共卫生事件舆情传播与演变——以2018年疫苗事件为例[J]. 数据分析与知识发现, 2019, 3(4):42-52.
[3] ( Wang Lin, Wang Ke, Wu Jiang. Public Opinion Propagation and Evolution of Public Health Emergencies in Social Media Era: A Case Study of 2018 Vaccine Event[J]. Data Analysis and Knowledge Discovery, 2019, 3(4):42-52.)
[4] 周晶晶. 网络意见领袖的分类、形成与反思[J]. 今传媒, 2019, 27(5):42-44.
[4] ( Zhou Jingjing. Classification, Formation and Reflection of Network Opinion Leaders[J]. Today's Massmedia, 2019, 27(5):42-44.)
[5] 马超. 健康议题辟谣社群的类别构成与社群结构研究——基于多主体谣言协同治理的视角[J]. 情报杂志, 2019, 38(1):96-105.
[5] ( Ma Chao. Study on the Categories and Structure of Health Rumor Denials Community: From the Perspective of Rumor Cooperative Governance[J]. Journal of Intelligence, 2019, 38(1):96-105.)
[6] 肖雪, 陈云伟, 邓勇. 引文网络的社团划分研究进展综述[J]. 情报杂志, 2016, 35(4):125-130.
[6] ( Xiao Xue, Chen Yunwei, Deng Yong. Development of Community Discovery in Citation Networks[J]. Journal of Intelligence, 2016, 35(4):125-130.)
[7] 刘传建. 复杂网络中的社团结构划分及分析应用[D]. 济南: 山东大学, 2014.
[7] ( Liu Chuanjian. Community Detection and Analytical Application in Complex Networks[D]. Jinan: Shandong University, 2014.)
[8] 陈芬, 付希, 何源, 等. 融合社会网络分析与影响力扩散模型的微博意见领袖发现研究[J]. 数据分析与知识发现, 2018, 2(12):60-67.
[8] ( Chen Fen, Fu Xi, He Yuan, et al. Identifying Weibo Opinion Leaders with Social Network Analysis and Influence Diffusion Model[J]. Data Analysis and Knowledge Discovery, 2018, 2(12):60-67.)
[9] 张绍武, 尹杰, 林鸿飞, 等. 基于用户分析的微博用户影响力度量模型[J]. 中文信息学报, 2015, 29(4):59-66.
[9] ( Zhang Shaowu, Yin Jie, Lin Hongfei, et al. A Micro-blog User Influential Model Based on User Analysis[J]. Journal of Chinese Information Processing, 2015, 29(4):59-66.)
[10] Chorley M J, Colombo G B, Allen S M, et al. Human Content Filtering in Twitter: The Influence of Metadata[J]. International Journal of Human - Computer Studies, 2015, 74:32-40.
doi: 10.1016/j.ijhcs.2014.10.001
[11] 徐冰村, 张晓冬. 开源社区中的意见领袖识别及跟随效应仿真[J]. 情报理论与实践, 2019, 42(12):101-107.
[11] ( Xu Bingcun, Zhang Xiaodong. Opinion Leader Identification and Following Effect Simulation in the Open Source Community[J]. Information Studies: Theory & Application, 2019, 42(12):101-107.)
[12] 吴渝, 马璐璐, 林茂, 等. 基于用户影响力的意见领袖发现算法[J]. 小型微型计算机系统, 2015, 36(3):561-565.
[12] ( Wu Yu, Ma Lulu, Lin Mao, et al. Discovery Algorithm of Opinion Leaders Based on User Influence[J]. Journal of Chinese Computer Systems, 2015, 36(3):561-565.)
[13] 钟磊, 宋香荣, 孙瑞娜. 基于LeaderRank的意见领袖发现模型及其应用[J]. 情报杂志, 2021, 40(4):194-199.
[13] ( Zhong Lei, Song Xiangrong, Sun Ruina. Opinion Leader Discovery Model Based on LeaderRank and Its Application[J]. Journal of Intelligence, 2021, 40(4):194-199.)
[14] 张玉晨, 翟姗姗, 许鑫, 等. 微博“中V”用户的传播特征及其引导力研究——以罗一笑事件为例[J]. 图书情报工作, 2018, 62(11):79-87.
[14] ( Zhang Yuchen, Zhai Shanshan, Xu Xin, et al. Research on the Propagation Features and Guidance of the Mid-class Verified User Based on the Microblog——Taking the Case of Yixiao Luo as an Example[J]. Library and Information Service, 2018, 62(11):79-87.)
[15] 周庆安, 宁雨奇. 唤醒、愉悦与支配:情感作用下的推特政治传播路径重构[J]. 现代传播(中国传媒大学学报), 2020, 42(11):53-59.
[15] ( Zhou Qing'an, Ning Yuqi. Arousal, Pleasure, Domination: Restructuring the Political Transmission Path of Twitter Under the Influence of Emotion[J]. Modern Communication (Journal of Communication University of China), 2020, 42(11):53-59.)
[16] 安璐, 胡俊阳, 李纲. 突发事件情境下社交媒体高影响力用户画像研究[J]. 情报资料工作, 2020, 41(6):6-16.
[16] ( An Lu, Hu Junyang, Li Gang. Research on Portraits of High-impact Users on Social Media in the Context of Emergencies[J]. Information and Documentation Services, 2020, 41(6):6-16.)
[17] 朱庆华, 李亮. 社会网络分析法及其在情报学中的应用[J]. 情报理论与实践, 2008, 31(2):179-183, 174.
[17] ( Zhu Qinghua, Li Liang. Social Network Analysis Method & Its Application in Information Science[J]. Information Studies: Theory & Application, 2008, 31(2):179-183, 174.)
[18] Blondel V D, Guillaume J L, Lambiotte R, et al. Fast Unfolding of Communities in Large Networks[J]. Journal of Statistical Mechanics: Theory and Experiment, 2008(10): Article No. 10008.
[19] 汤志伟, 龚泽鹏, 郭雨晖. 基于二维分析框架的中美开放政府数据政策比较研究[J]. 中国行政管理, 2017(7):41-48.
[19] ( Tang Zhiwei, Gong Zepeng, Guo Yuhui. A Comparative Study on Sino-US Open Government Data Policies Based on Two-Dimensional Analysis Framework[J]. Chinese Public Administration, 2017(7):41-48.)
[20] 杜群阳, 朱剑光, 倪春平, 等. 国际化企业创业导向: 基于二维分析框架的理论与实证研究[J]. 中国工业经济, 2010(9):141-150.
[20] ( Du Qunyang, Zhu Jianguang, Ni Chunping, et al. International Enterprises' Entrepreneurship Orientation: Theoretical and Empirical Based on Bidimensional Analytical Framework[J]. China Industrial Economics, 2010(9):141-150.)
[21] Freeman L C. Centrality in Social Networks Conceptual Clarification[J]. North-Holland, 1978, 1(3):215-239.
[22] 韩运荣, 高顺杰 微博舆论中的意见领袖素描——一种社会网络分析的视角[J]. 新闻与传播研究, 2012, 19(3):61-69.
[22] ( Han Yunrong, Gao Shunjie. Sketch of Opinion Leaders in Microblog Public Opinion——A Perspective of Social Network Analysis[J]. Journalism & Communication, 2012, 19(3):61-69.)
[23] 王晰巍, 张柳, 韦雅楠, 等. 社交网络舆情中意见领袖主题图谱构建及关系路径研究——基于网络谣言话题的分析[J]. 情报资料工作, 2020, 41(2):47-55.
[23] ( Wang Xiwei, Zhang Liu, Wei Ya'nan, et al. Research on Thematic Map Construction and Relationship Path of Opinion Leaders in Social Network Public Opinion: An Analysis Based on Internet Rumor Topics[J]. Information and Documentation Services, 2020, 41(2):47-55.)
[24] 朱志国, 张翠, 丁学君, 等. 基于熵权灰色关联模型的重大突发舆情意见领袖识别研究[J]. 情报学报, 2017, 36(7):706-714.
[24] ( Zhu Zhiguo, Zhang Cui, Ding Xuejun, et al. Research on Opinion Leader Identification of Major Unexpected Public Opinion Based on Entropy Weight Grey Correlation Model[J]. Journal of the China Society for Scientific and Technical Information, 2017, 36(7):706-714.)
[25] 徐淑琼. 社会网络影响力最大化研究及其网络营销应用[D]. 南京: 东南大学, 2015.
[25] ( Xu Shuqiong. Research on Maximization of Social Network Influence and Its Application in Network Marketing[D]. Nanjing: Southeast University, 2015.)
[26] Mehrabian A. Framework for a Comprehensive Description and Measurement of Emotional States[J]. Genetic, Social, and General Psychology Monographs, 1995, 121(3):339-361.
[27] 张信勇. LIWC:一种基于语词计量的文本分析工具[J]. 西南民族大学学报(人文社会科学版), 2015, 36(4):101-104.
[27] ( Zhang Xinyong. LIWC: A Text Analysis Tool Based on Word Measurement[J]. Journal of Southwest Minzu University(Humanities and Social Science), 2015, 36(4):101-104.)
[28] Schultheiss O C. Are Implicit Motives Revealed in Mere Words? Testing the Marker-Word Hypojournal with Computer-Based Text Analysis[J]. Frontiers in Psychology, 2013, 4: Article No. 748.
[29] Kacewicz E, Pennebaker J W, Davis M, et al. Pronoun Use Reflects Standings in Social Hierarchies[J]. Journal of Language and Social Psychology, 2014, 33(2):125-143.
doi: 10.1177/0261927X13502654
[30] Twitter. Verified Account[EB/OL](2020-12-17)[2021-02-03]. https://help.twitter.com/en/managing-your-account/about-twitter-verified-accounts
[31] 刘峣. 中国声音如何唱响海外舆论场?主动出击占领平台[J]. 人民日报海外版, 2015-06-12.
[31] (Liu Yao. How can China's Voice be Heard in Overseas Opinion Field? Take the Initiative to Occupy the Platform[J]. People's Daily Overseas Edition, 2015-06-12).
[1] 钟佳娃,刘巍,王思丽,杨恒. 文本情感分析方法及应用综述*[J]. 数据分析与知识发现, 2021, 5(6): 1-13.
[2] 王晰巍,贾若男,韦雅楠,张柳. 多维度社交网络舆情用户群体聚类分析方法研究*[J]. 数据分析与知识发现, 2021, 5(6): 25-35.
[3] 马莹雪,赵吉昌. 自然灾害期间微博平台的舆情特征及演变*——以台风和暴雨数据为例[J]. 数据分析与知识发现, 2021, 5(6): 66-79.
[4] 刘彤,刘琛,倪维健. 多层次数据增强的半监督中文情感分析方法*[J]. 数据分析与知识发现, 2021, 5(5): 51-58.
[5] 王雨竹,谢珺,陈波,续欣莹. 基于跨模态上下文感知注意力的多模态情感分析 *[J]. 数据分析与知识发现, 2021, 5(4): 49-59.
[6] 常城扬,王晓东,张胜磊. 基于深度学习方法对特定群体推特的动态政治情感极性分析*[J]. 数据分析与知识发现, 2021, 5(3): 121-131.
[7] 徐雅斌, 孙秋天. 特定舆情的意见领袖挖掘和关键传播路径预测[J]. 数据分析与知识发现, 2021, 5(2): 32-42.
[8] 张梦瑶, 朱广丽, 张顺香, 张标. 基于情感分析的微博热点话题用户群体划分模型 *[J]. 数据分析与知识发现, 2021, 5(2): 43-49.
[9] 余本功, 张书文. 基于BAGCNN的方面级别情感分析研究*[J]. 数据分析与知识发现, 2021, 5(12): 37-47.
[10] 韩普, 张伟, 张展鹏, 王宇欣, 方浩宇. 基于特征融合和多通道的突发公共卫生事件微博情感分析*[J]. 数据分析与知识发现, 2021, 5(11): 68-79.
[11] 吕华揆,刘政昊,钱宇星,洪旭东. 异质性财经新闻与股市关系研究*[J]. 数据分析与知识发现, 2021, 5(1): 99-111.
[12] 徐红霞,于倩倩,钱力. 基于主题模型和情感分析的话题交互数据观点对抗性分析 *[J]. 数据分析与知识发现, 2020, 4(7): 110-117.
[13] 姜霖,张麒麟. 基于引文细粒度情感量化的学术评价研究*[J]. 数据分析与知识发现, 2020, 4(6): 129-138.
[14] 石磊,王毅,成颖,魏瑞斌. 自然语言处理中的注意力机制研究综述*[J]. 数据分析与知识发现, 2020, 4(5): 1-14.
[15] 李铁军,颜端武,杨雄飞. 基于情感加权关联规则的微博推荐研究*[J]. 数据分析与知识发现, 2020, 4(4): 27-33.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn