Please wait a minute...
Data Analysis and Knowledge Discovery  2019, Vol. 3 Issue (11): 120-128    DOI: 10.11925/infotech.2096-3467.2018.1255
Current Issue | Archive | Adv Search |
Identifying Weibo Opinion Leaders with Text Sentiment Analysis
Fen Chen1,2(),Xiaohuan Gao1,Yue Peng1,Yuan He1,Chunxiang Xue1,2
1 School of Economics and Management, Nanjing University of Science and Technology, Nanjing 210094, China
2 Jiangsu Collaborative Innovation Center of Social Safety Science and Technology, Nanjing 210094, China, Nanjing 210094, China
Download: PDF (569 KB)   HTML ( 11 ) 
Export: BibTeX | EndNote (RIS)      
Abstract  

[Objective] This study combines the external features and contents of the Weibo posts, aiming to identify online opinion leaders with the help of text sentiment analysis. [Methods] First, we identified the potential opinion leaders and introduced the Word2Vec algorithm to find new sentiment words. Then, we conducted sentiment analysis to categorize the texts as positive, negative or neutral ones. Finally, we detected and removed bloggers attracted too many negative comments. [Results] The proposed model optimized the ranking of opinion leaders, which was better than the improved PageRank algorithm, and more consistent with the Weibo data. [Limitations] We only examined our model with one piece of breaking news. [Conclusions] This paper identifies three types of online opinion leaders from the public reaction in emergency.
Key words： Text Sentiment Analysis      Opinion Leader      Weibo     
Received: 12 November 2018      Published: 18 December 2019
ZTFLH:  G206  
Corresponding Authors: Fen Chen     E-mail: Lanyan_js@126.com
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Fen Chen
Xiaohuan Gao
Yue Peng
Yuan He
Chunxiang Xue

Cite this article:

Fen Chen,Xiaohuan Gao,Yue Peng,Yuan He,Chunxiang Xue. Identifying Weibo Opinion Leaders with Text Sentiment Analysis. Data Analysis and Knowledge Discovery, 2019, 3(11): 120-128.

URL:

https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/10.11925/infotech.2096-3467.2018.1255     OR     https://manu44.magtech.com.cn/Jwk_infotech_wk3/EN/Y2019/V3/I11/120

方法 主要思想
传统方法[4,5,6] 主观判断法, 自我报告法, 关键人物访谈法等
社会网络分析法[7,8,9,10,11,12] 根据各节点在网络中的交互关系构建网络结构, 据此识别意见领袖
PageRank法[13,14,15,16,17] 借鉴PageRank思想, 将微博用户之间的交互关系类比为传统网页之间的链接, 构建与微博用户转发、评论相对应的有向关系图
指标分析法[18,19,20,21,22,23,24] 分析意见领袖的典型特征, 建立识别意见领袖的指标体系, 通常包括一级指标类和二级指标项
影响力(0.6651) 活跃度(0.1038) 专业性(0.2311)
粉丝数 0.1208 原创微博数 0.0707 是否认证 0.1245
被@数 0.0915 关注人数 0.0122 行业性 0.0687
被转发数 0.2519 回复他人数 0.0209 媒介接触度 0.0379
被评论数 0.2009
关系 含义 实例
advmod副词性修饰语 用于改变副词的强度 “战争原本相当残酷, 将战争美化到如同娱乐活动一般, 让人反感”: advmod(残酷-4, 相当-3), 表示“相当”作为副词修饰了“残酷”这个形容词
amod形容词修饰语 修饰名词词组 “近来风靡荧屏的抗日题材电视剧, 越来越类型化”: amod(电视剧-7, 抗日-5), 表示名词性形容词“抗日”修饰了“电视剧”
nsubj名词性主语 修饰名词性主语 “不一样的抗日神剧, 好看！”: nsubj(好看-8, 剧-6), 表示“好看”修饰了名词性主语“剧”
neg否定修饰词 含义反转 “有人说剧情俗套抗日神剧神马的, 我倒觉得不错, 因为不该死的一个没死, 看着不郁闷”: neg(郁闷-28, 不-27), 表示“不”对“郁闷”进行了否定
程度级别 词语(示例) 权重 数量
“极其|extreme/最|most” 百分之百、绝对、极其 3 69
“很|very” 颇为、格外、实在 2 42
“较|more” 多、越是、较为 1 37
“稍|-ish” 稍、略为、一点 1/2 29
“欠|insufficiently” 不甚、微、没怎么 -1/2 12
“超|over” 过头、过分、偏 -1 30
标点符号 权重 标点符号 权重
“！！” 2 “。。。”、“···” 1/2
“, ”、“。” 1 “?”、“?！” -1/2
微博昵称 粉丝数 被@数 被转发数 被评论数 原创微博数 回复他人数 …… 媒体接触度 领袖值
头条新闻 1.000000000 0.231958763 1.000000000 1.000000000 1.000000000 0.000000000 …… 1.000000000 0.829111545
央视新闻 0.530858376 1.000000000 0.764969581 0.624107143 0.343150772 0.003816794 …… 0.739583333 0.651347868
八卦_我实在是太CJ了 0.100473289 0.046391753 0.691642651 0.638149351 0.04363392 0.026717557 …… 0.308035714 0.461397104
江苏身边事 0.006707475 0.054982818 0.74871918 0.260227273 0.221865622 0.003816794 …… 0.410714286 0.412328209
人民日报 0.590243392 0.577319588 0.240954211 0.111850649 0.307349176 0.003816794 …… 0.342261905 0.367892438
博主昵称 “伪领袖”
可能性		 博主昵称 “伪领袖”
可能性
1 头条新闻 7.9% 9 财经网 8.4%
2 央视新闻 10% 10 评论员李铁 17.4%
3 八卦_我实在是太CJ了 9.6% 11 南方都市报 12.2%
4 江苏身边事 17.6% 12 泉在流淌 11%
5 人民日报 10.8% 13 孟祥远 12%
6 赖清辉 12.4% 14 暗访小王子 13.6%
7 南京发布 9.6% 15 创业家杂志 17.5%
8 宋坚 -
排名 本方法意见领袖 基于改进的PageRank意见领袖
1 头条新闻 新浪江苏
2 央视新闻 央视新闻
3 八卦_我实在是太CJ了 南京鼓楼医院
4 江苏身边事 江苏身边事
5 人民日报 人民日报
6 赖清辉 南京日报
7 南京发布 南方都市报
8 宋坚 财经网
9 财经网 环球时报
10 评论员李铁 南京发布
11 南方都市报 头条新闻
12 泉在流淌 新浪新闻视频
13 孟祥远 马伯庸
14 暗访小王子 法制日报
15 创业家杂志 评论员李铁
[1] 新浪科技. 微博发布2019年第一季度财报[R/OL]. [2019-11-05]. https://tech.sina.com.cn/i/2019-05-23/doc-ihvhiews4060412.shtml.
[1] ( Sina. Sina Weibo Released the 1st Quarterly Financial Reporting(2019)[R/OL]. [2019-11-05]. https://tech.sina.com.cn/i/2019-05-23/doc-ihvhiews4060412.shtml .)
[2] 刘志明, 刘鲁 . 微博网络舆情中的意见领袖识别及分析[J]. 系统工程, 2011,29(6):8-16.
[2] ( Liu Zhiming, Liu Lu . Recognition and Analysis of Opinion Leaders in Microblog Public Opinions[J]. Systems Engineering, 2011,29(6):8-16.)
[3] Lazarsfeld P F, Berelson B, Gaudet H. The People’s Choice[M]. New York: Columbia University Press, 1948.
[4] Rogers E M, Cartano D G . Living Research Methods of Measuring Opinion Leadership[J]. Public Opinion Quarterly, 1962,26(3):435-441.
doi: 10.1111/j.1365-2834.2010.01132.x pmid: 20840368
[5] Doumit G, Wright F C, Graham I D , et al. Opinion Leaders and Changes over Time: A Survey[J]. Implementation Science, 2011, 6: Article No.117.
doi: 10.1186/1748-5908-6-133 pmid: 22204440
[6] Lyons B, Henderson K . Opinion Leadership in a Computer-Mediated Environment[J]. Journal of Consumer Behaviour, 2005,4(5):319-329.
doi: 10.1002/(ISSN)1479-1838
[7] Jain L, Katarya R, Sachdeva S . Opinion Leader Detection Using Whale Optimization Algorithm in Online Social Network[J]. Expert Systems with Applications. https://doi.org/10.1016/j.eswa. 2019. 113016.
[8] Chen Y C, Cheng J Y, Hsu H H . A Cluster-Based Opinion Leader Discovery in Social Network [C]// Proceedings of the 2016 Conference on Technologies and Applications of Artificial Intelligence. 2016: 78-83.
[9] Sun G X, Bin S . A New Opinion Leaders Detecting Algorithm in Multi-Relationship Online Social Networks[J]. Multimedia Tools Application, 2018,77:4295-4307.
doi: 10.1007/s11042-017-4766-y
[10] Lei S J, Zhang X D, Yan Y N . Research on Opinion Leaders Recognition Based on TOPSIS in Open Source Design Community [C]//Proceedings of the 23rd International Conference on Computer Supported Cooperative Work in Design. IEEE, 2019.
[11] 魏思敏, 张宪华, 张祯 , 等. 基于复杂网络的虚拟品牌社区意见领袖识别研究——以魅族Flyme社区为例[J]. 山东大学学报: 理学版, 2018,53(11):26-34.
[11] ( Wei Simin, Zhang Xianhua, Zhang Zhen , et al. Virtual Brand Community Opinion Leader Recognition Based on Complex Network—— Example of the Meizu Flyme Community[J]. Journal of Shandong University: Natural Science, 2018,53(11):26-34.)
[12] Dewi F K, Yudhoatmojo S B, Budi I . Identification of Opinion Leader on Rumor Spreading in Online Social Network Twitter Using Edge Weighting and Centrality Measure Weighting [C]// Proceedings of the 12th International Conference on Digital Information Management. 2017: 313-318.
[13] Qiu L Q, Dai J L, Liu H Y , et al. Detecting Opinion Leaders in Online Social Networks Using HybridRank Algorithm[J]. Journal of Intelligent & Fuzzy Systems, 2018,35:513-522.
doi: 10.1097/IAE.0000000000002717 pmid: 31842189
[14] Tsao H W, Chen C M, You Z L . Community Detection with Opinion Leaders’ Identification for Promoting Collaborative Problem Based Learning Performance[J]. International Congress on Advanced Applied Informatics, 2018: 158-163.
[15] 许宁菲, 程生雪, 王虎 , 等. 基于ActivityRank算法的社会化电商意见领袖识别[J]. 现代商贸工业, 2019(15):47-49.
[15] ( Xu Ningfei, Cheng Shengxue, Wang Hu , et al. Recognition of Social E-commerce Opinion Leaders Based on ActivityRank Algorithm[J]. Modern Business Trade Industry, 2019(15):47-49.)
[16] Ma N, Liu Y J . SuperedgeRank Algorithm and Its Application in Identifying Opinion Leader of Online Public Opinion Supernetwork[J]. Expert Systems with Applications, 2014,41(4):1357-1368.
doi: 10.1016/j.eswa.2013.08.033
[17] 熊涛, 何跃 . 微博转发网络中意见领袖的识别与分析[J]. 现代图书情报技术, 2013(6):55-62.
[17] ( Xiong Tao, He Yue . The Identification and Analysis of Micro-Blogging Opinion Leaders in the Network of Retweet Relationship[J]. New Technology of Library and Information Service, 2013(6):55-62.)
[18] 王佳敏, 吴鹏, 陈芬 , 等. 突发事件中意见领袖的识别和影响力实证研究[J]. 情报学报, 2016,35(2):169-176.
[18] ( Wang Jiamin, Wu Peng, Chen Fen , et al. Empirical Study on Recognition and Influence of Opinion Leaders in Emergency[J]. Journal of the China Society for Scientific and Technical Information, 2016,35(2):169-176.)
[19] Aleahmad A, Karisani P, Rahgozar M , et al. OLFinder: Finding Opinion Leaders in Online Social Networks[J]. Journal of Information Science, 2016,42(5):659-674.
doi: 10.1177/0165551515605217
[20] 吴江, 赵颖慧, 高嘉慧 . 医疗舆情事件的微博意见领袖识别与分析研究[J]. 数据分析与知识发现, 2019,3(4):53-62.
[20] ( Wu Jiang, Zhao Yinghui, Gao Jiahui . Research on Weibo Opinion Leaders Identification and Analysis in Medical Public Opinion Incidents[J]. Data Analysis and Knowledge Discovery, 2019,3(4):53-62.)
[21] 王延隆 . 网络意见领袖的识别分析、产生逻辑及其应用[J]. 河南工业大学学报: 社会科学版, 2019,15(4):76-83.
[21] ( Wang Yanlong. The Identification , Generating Logic and Application of Network Opinion Leader[J]. Journal of Henan University of Technology: Social Science, 2019,15(4):76-83.)
[22] 安璐, 胡俊阳, 李纲 . 基于主题一致性和情感支持的评论意见领袖识别方法研究[J]. 管理科学, 2019,32(1):3-13.
[22] ( An Lu, Hu Junyang, Li Gang . A Method of Identifying Comment Opinion Leaders Based on Topic Consistency and Emotional Support[J]. Journal of Management Science, 2019,32(1):3-13.)
[23] 童莉莉, 李荣禄, 闫强 . 在线知识社群中的意见领袖识别模型研究[J]. 中国电化教育, 2019(3):97-103.
[23] ( Tong Lili, Li Ronglu, Yan Qiang . Research on Opinion Leader Identification Model in Online Knowledge Community[J]. China Educational Technology, 2019(3):97-103.)
[24] 王家合, 杨倩文 . 自媒体时代意见领袖的识别与引导对策研究——基于议程设置理论视角[J]. 湖北社会科学, 2019(1):181-188.
[24] ( Wang Jiahe, Yang Qianwen . Research on Identification and Guidance of Opinion Leaders in the Media Age[J]. Hubei Social Sciences, 2019(1):181-188.)
[25] Watts D J, Dodds P S . Influentials, Networks, Public Opinion Formation[J]. Journal of Consumer Research, 2007,34(4):441-458.
doi: 10.1086/518527
[26] Rogers E M . Diffusion of Innovations[M]. Simon and Schuster, 2010.
[27] NLPIR[EB/OL]. [ 2015- 12- 02]. http://ictclas.nlpir.org .
[28] Standford Parser[EB/OL]. [ 2015- 12- 20]. http://nlp.stanford.edu/software/lex-parser.html .
[29] HowNet: Beta[EB/OL]. [ 2015- 12- 25]. http://www.keenage.com/html/c_index.html .
[30] Word2Vec[EB/OL]. [ 2014- 03- 02]. http://word2vec.googlecode.com/svn/trunk .
[31] 霍宗凡 . 基于语义的文本倾向性分析与研究[D]. 南京: 南京邮电大学, 2011.
[31] ( Huo Zongfan . Analysis and Research of Text Orientation Based on Semantic[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2011.)
[1] Xu Yabin, Sun Qiutian. Identifying Leaders and Dissemination Paths of Public Opinion[J]. 数据分析与知识发现, 2021, 5(2): 32-42.
[2] Qiu Erli,He Hongwei,Yi Chengqi,Li Huiying. Research on Public Policy Support Based on Character-level CNN Technology[J]. 数据分析与知识发现, 2020, 4(7): 28-37.
[3] Wang Xiwei,Zhang Liu,Huang Bo,Wei Ya’nan. Constructing Topic Graph for Weibo Users Based on LDA: Case Study of “Egypt Air Disaster”[J]. 数据分析与知识发现, 2020, 4(10): 47-57.
[4] Jiang Wu,Yinghui Zhao,Jiahui Gao. Research on Weibo Opinion Leaders Identification and Analysis in Medical Public Opinion Incidents[J]. 数据分析与知识发现, 2019, 3(4): 53-62.
[5] Chen Fen,Fu Xi,He Yuan,Xue Chunxiang. Identifying Weibo Opinion Leaders with Social Network Analysis and Influence Diffusion Model[J]. 数据分析与知识发现, 2018, 2(12): 60-67.
[6] He Yue,Zhu Can. Sentiment Analysis of Weibo Opinion Leaders——Case Study of “Illegal Vaccine” Event[J]. 数据分析与知识发现, 2017, 1(9): 65-73.
[7] Xiong Tao, He Yue. The Identification and Analysis of Micro-blogging Opinion Leaders in the Network of Retweet Relationship[J]. 现代图书情报技术, 2013, (6): 55-62.
  Copyright © 2016 Data Analysis and Knowledge Discovery   Tel/Fax:(010)82626611-6626，82624938   E-mail:jishu@mail.las.ac.cn