INFORMATION RESEARCH

Screening Methods of Opinion Leaders in Health Super Topic and Its Guiding Effect on Different Participation Behaviors

  • Jin Yan ,
  • Liu Wenjin ,
  • Bi Chongwu
Expand
  • 1 School of Information Management, Zhengzhou University, Zhengzhou 450001;
    2 Zhengzhou Data Science Research Center, Zhengzhou 450001

Received date: 2022-09-02

  Revised date: 2022-10-08

  Online published: 2023-03-04

Abstract

[Purpose/Significance] There are formal opinion leaders based on rule setting and real opinion leaders who play a practical role in health super topic. It is helpful for the management and development of health super topic to identify the real opinion leaders and analyze their guiding on different types of users' participation behaviors.[Method/Process] Firstly, a three-level opinion leader identify model was constructed from three attributes of user activity, topic relevance and network location. Secondly, the influence of opinion leaders was quantified to analyze the guiding effect of opinion leaders in healthy super topic. Finally, taking "systemic lupus erythematosus (sle)" healthy topic as an example was for empirical study.[Result/Conclusion] The three-level model can filter out the actual opinion leaders in the health super topic and its identify effect is better than that of the single attribute identification method. Opinion leaders have a positive guiding effect on the information dissemination in health super topic, and have an impact on users of different participation types and their different participation behaviors.

Cite this article

Jin Yan , Liu Wenjin , Bi Chongwu . Screening Methods of Opinion Leaders in Health Super Topic and Its Guiding Effect on Different Participation Behaviors[J]. Library and Information Service, 2023 , 67(4) : 91 -101 . DOI: 10.13266/j.issn.0252-3116.2023.04.009

References

[1] 超级话题指导手册[EB/OL].[2022-03-28].https://weibo.com/ttarticle/p/show?id=2309404057738014492456.
[2] LAZARSFELD P F, BERELSON B, GAUDET H.The people's choice[M].New York:Columbia University Press, 1948.
[3] 汪雅倩.从名人到"微名人":移动社交时代意见领袖的身份变迁及影响研究[J].新闻记者, 2021(3):27-39.
[4] 李佳.数媒时代意见领袖的变迁、边界与进路[J].青年记者, 2021(7):58-59.
[5] 徐翔, 夏敏.从"意见领袖"到"情感领袖":微博意见领袖的情感特征研究[J].重庆邮电大学学报(社会科学版), 2021, 33(6):157-169.
[6] 生奇志, 高森宇.中国微博意见领袖:特征、类型与发展趋势[J].东北大学学报(社会科学版), 2013, 15(4):381-385.
[7] 邓君, 钟楚依, 常严予, 等.基于两级传播理论的在线健康社区意见领袖交互行为研究——以百度"自闭症吧"为例[J].情报理论与实践, 2022, 45(1):127-133, 111.
[8] 李纲, 陈璟浩.突发公共事件网络舆情研究综述[J].图书情报知识, 2014, 32(2):111-119.
[9] 王晰巍, 贾玺智, 刘婷艳, 等.区块链环境下社交网络用户意见领袖识别与影响力研究[J].情报理论与实践, 2021, 44(5):84-91.
[10] 张米, 张晖, 杨春明, 等.基于多特征信息传播模型的微博意见领袖挖掘[J].中文信息学报, 2018, 32(2):129-138, 146.
[11] 陈波, 唐相艳, 于泠, 等.基于胜任力模型的社交网络意见领袖识别方法[J].通信学报, 2014, 35(11):12-22.
[12] REHMAN A U, JIANG A, REHMAN A, et al.Identification and role of opinion leaders in information diffusion for online discussion network[J].Journal of ambient intelligence and humanized computing, 2020, 11(1):1-13.
[13] 朱茂然, 林星凯, 陆頲, 等.基于情感分析的社交网络意见领袖的识别——以汽车论坛为例[J].情报理论与实践, 2017, 40(6):76-81.
[14] 刘高勇, 谭依雯, 艾丹祥, 等.基于观点挖掘的突发事件微博意见领袖识别方法[J].广东工业大学学报, 2021, 38(4):41-51.
[15] 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.
[16] 张柳, 王晰巍, 黄博, 等.基于LDA模型的新冠肺炎疫情微博用户主题聚类图谱及主题传播路径研究[J].情报学报, 2021, 40(3):234-244.
[17] 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.
[18] 陈远, 刘欣宇.基于社会网络分析的意见领袖识别研究[J].情报科学, 2015, 33(4):13-19, 92.
[19] JAIN L, KATARYA R, SACHDEVA S.Opinion leader detection using whale optimization algorithm in online social network[J].Expert systems with applications, 2019, 142(5920):113016.
[20] JAIN L, KATARYA R.Discover opinion leader in online social network using firefly algorithm[J].Expert systems with applications, 2019, 122(MAY):1-15.
[21] 李美子, 米一菲, 张倩, 等.社交网络中基于K核分解的意见领袖识别算法[J].计算机应用, 2022, 42(1):26-35.
[22] 郭奕, 徐亮, 熊雪军.社交网络中意见领袖挖掘方法综述[J].计算机科学与探索, 2021, 15(11):2077-2092.
[23] 王嘉麒, 杜义华, 赵以霞.基于综合影响力和情感特征的意见领袖发现方法[J].数据与计算发展前沿, 2021, 3(4):126-139.
[24] 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.
[25] 饶珊, 曾明.新冠肺炎疫情下的新意见领袖及其舆论引导作用[J].新媒体公共传播, 2021, 2(2):61-69.
[26] 严炜炜, 王玲, 程子洁.视频分享平台意见领袖特征及其形成路径研究[J].情报科学, 2021, 39(5):27-33.
[27] KLIESTIK T, ŠTEFAN Z, MÁRIA H.The impact of opinion leaders on the consumer behaviour in the global digital environment[J].SHS Web of conferences, 2021, 92(5):06043.
[28] 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.
[29] 王晨旭, 管晓宏, 秦涛, 等.微博消息传播中意见领袖影响力建模研究[J].软件学报, 2015, 26(6):1473-1485.
[30] 李冉, 王佳英, 单菁, 等.突发事件微博网络舆情分析及可视化——以"武汉封城"为例[J].情报探索, 2022, 36(2):67-72.
[31] WENG J S, LIM E P, JIANG J, et al.Twitterrank:finding topic sensitive influential Twitterers[C]//Proceedings of the 3rd ACM international conference on Web search and data mining.New York:ACM, 2010:261-270.
[32] 郭博, 许昊迪, 雷水旺.知乎平台用户影响力分析与关键意见领袖挖掘[J].图书情报工作, 2018, 62(20):122-132.
[33] BLEI D M, NG A Y, JORDAN M I.Latent dirichlet allocation[J].Journal of machine learning research, 2003, 3(Jan):993-1022.
[34] KATZ E, GUREVITCH H M.On the use of the mass media for important things[J].American sociological review, 1973, 38(2):164-181.
[35] 赵宇晴, 阮平南, 刘晓燕, 等.基于在线评论的用户满意度评价研究[J].管理评论, 2020, 32(3):179-189.
[36] 张靖, 段富.优化初始聚类中心的改进k-means算法[J].计算机工程与设计, 2013, 34(5):1691-1694, 1699.
[37] 杨静雅, 孙林夫, 吴奇石.基于半监督谱聚类集成的售后客户细分[J].计算机工程与应用, 2020, 56(2):266-271.
[38] 王荻智, 李建宏, 施运梅.基于K-means的政府公文聚类方法[J].软件导刊, 2020, 19(6):201-204.
[39] CIALDINI R B.Influence:science and practice[M].4th ed.Boston:Allyn & Bacon, 2001.
Outlines

/