主管:中国科学院
主办:中国优选法统筹法与经济数学研究会
   中国科学院科技战略咨询研究院

文本主题特征和医疗众筹筹资绩效:基于LDA模型的研究

  • 蒋志强 ,
  • 陶屹 ,
  • 崔岩 ,
  • 周炜星
展开
  • 华东理工大学商学院,上海 200237
蒋志强(1982-),男(汉族),江苏宜兴人,华东理工大学商学院,教授,博士,研究方向:合作行为、风险管理,E-mail:zqjiang@ecust.edu.cn.

收稿日期: 2022-06-16

  修回日期: 2023-03-03

  网络出版日期: 2025-08-06

基金资助

国家自然科学基金项目(72171084);国家自然科学基金项目(91746108)

Extracting the Topics Affecting Fundraising Performance from Medical Crowdfunding Descriptions Based on the LDA Model

  • Zhiqiang Jiang ,
  • Yi Tao ,
  • Yan Cui ,
  • Weixing Zhou
Expand
  • School of Business,East China University of Science and Technology,Shanghai 200237,China

Received date: 2022-06-16

  Revised date: 2023-03-03

  Online published: 2025-08-06

摘要

网络公益众筹是“互联网+公益”的跨界融合,也是大病医疗救助的重要组成部分。如何激发大众的援助意愿,提升公益众筹项目的筹款效率,对求助家庭有重要意义。项目描述是众筹项目信息披露的重要途径,直接影响着潜在捐赠者的捐赠意愿,因此,本文基于轻松筹平台,探索了众筹项目文本信息对筹资绩效的影响。基于亚里士多德修辞理论的三大说服策略——信用策略、理性策略和情感策略,本文利用LDA模型对110329个医疗众筹项目的文本描述进行分析,提取出10个主题,并构造了6个主题变量:信用策略下的树立形象主题,理性策略下的疾病叙述主题、治疗费用主题,以及情感策略下的家庭与亲情主题、劝捐与感激主题、积极叙事主题。研究表明,强调病情、费用和积极叙事的主题能显著促进项目筹款,而突出树立形象、家庭与亲情和劝捐与感激的主题对项目筹资有显著的负向作用。此外,主题数量的增加会增强劝捐与感激主题对筹资绩效的负面作用,但削弱了树立形象、治疗费用和积极叙事主题的效果。本研究对提高众筹筹资绩效,激发社会公众的爱心能量具有一定的理论和现实意义。

本文引用格式

蒋志强 , 陶屹 , 崔岩 , 周炜星 . 文本主题特征和医疗众筹筹资绩效:基于LDA模型的研究[J]. 中国管理科学, 2025 , 33(7) : 92 -104 . DOI: 10.16381/j.cnki.issn1003-207x.2022.1311

Abstract

Medical crowdfunding is an important channel to collect money to cover the medical expenses for poor families with severe illness. However, the fundraising performance of medical crowdfunding projects is still at a relatively low level. Therefore, to improve the fundraising performance, it is natural to stimulate more people to offer help. Project descriptions play a key role in disclosing crowdfunding project information and influencing potential donors. Therefore, the impact of crowdfunding project text information on fundraising performance is investigated, based on the data of 110329 medical crowdfunding projects from Qingsong Chou.The Latent Dirichlet allocation model is employed to analyze the potential semantics of project descriptions. Based on Aristotle's rhetorical theory of three persuasive strategies-credit strategy, rational strategy and emotional strategy, six topic variables are defined, that are (1)image-building (credit strategy), (2)disease narratives and (3)medical expenses (rational strategy), (4)family and affection, (5)persuasion and gratitude, and (6)positive narratives(emotional strategy). A linear regression model Y=αT+βC+Year+Province+γ+ϵ is built to quantify the impact of different topics on fundraising performance. Meanwhile, model Y=αT+δT×TopicNum+λTopicNum+βC+Year+Province+γ+ϵ is adopted to estimate the moderating effect of number of topics.The results indicate that topics emphasizing disease, expenses and positive narratives significantly improve the fundraising performance; Topics highlighting family and affection, persuasion and gratitude and image-building have a significantly negative effect on fundraising performance. Furthermore, an increase in the number of topics enhances the negative impact of persuasion and gratitude on fundraising performance, while diminishing the effects of image-building, medical expenses and positive narratives. These findings not only deepen the understanding of the effect of textual features on fundraising, but also provide new ideas for improving fundraising performance.

参考文献

[1] 张星, 赵越, 肖泉. 医疗众筹项目信息对捐赠效果的影响研究[J]. 管理学报202219(1): 85-92+101.
  Zhang X, Zhao Y, Xiao Q. A Study on the impacts of medical crowdfunding project information on donation effectiveness[J].Chinese Journal of Management202219(1): 85-92+101.
[2] Ren J, Raghupathi V, Raghupathi W. Understanding the dimensions of medical crowdfunding: A visual analytics approach[J]. Journal of Medical Internet Research202022(7): e18813.
[3] Zhang S, Zang X L, Zhang S N, et al. Social class priming effect on prosociality: Evidence from explicit and implicit measures[J]. International Journal of Environmental Research and Public Health202219(7): 3984.
[4] Zhao X H, Chen B L, Jin P. Inspired to donate: How donors' social class impacts charitable donations[J]. Journal of Consumer Behaviour202322(1): 3-13.
[5] Ba Z C, Zhao Y X, Song S J, et al. Understanding the determinants of online medical crowdfunding project success in China[J]. Information Processing & Management202158(2): 102465.
[6] Majumdar A, Bose I. My words for your pizza: An analysis of persuasive narratives in online crowdfunding[J]. Information & Management201855(6): 781-794.
[7] Loughran T, McDonald B. Measuring readability in financial disclosures[J]. The Journal of Finance201469(4): 1643-1671.
[8] 陈林, 谢彦妩, 李平, 等. 借款陈述文字中的违约信号——基于P2P网络借贷的实证研究[J]. 中国管理科学201927(4): 37-47.
  Chen L, Xie Y W, Li P, et al. The signal of default risk from the description-text based on the empirical research of P2P lending[J]. Chinese Journal of Management Science201927(4): 37-47.
[9] 沈艳, 陈赟, 黄卓. 文本大数据分析在经济学和金融学中的应用: 一个文献综述[J]. 经济学(季刊)201919(4): 1153-1186.
  Shen Y, Chen Y, Huang Z. A literature review of textual analysis in economic and financial research[J]. China Economic Quarterly201919(4): 1153-1186.
[10] 王韧, 刘于萍. 预期引导、政策冲击与股市波动——基于文本分析法的异质性诊断[J]. 统计研究202138(12): 118-130.
  Wang R, Liu Y P. Expectation guidance, policy shocks and volatility of stock market: Heterogeneous impact diagnosis based on text analysis method[J]. Statistical Research202138(12): 118-130.
[11] 姜富伟, 孟令超, 唐国豪. 媒体文本情绪与股票回报预测[J]. 经济学(季刊)202121(4): 1323-1344.
  Jiang F W, Meng L C, Tang G H. Media textual sentiment and Chinese stock return predictability[J]. China Economic Quarterly202121(4): 1323-1344.
[12] 俞红海, 范思妤, 吴良钰,等. 科创板注册制下的审核问询与IPO信息披露——基于LDA主题模型的文本分析[J]. 管理科学学报202225(8): 45-62.
  Yu H H, Fan S Y, Wu L Y, et al. Registration system review inquiry and IPO information disclosure on STAR market: Textual analysis based on LDA topic model[J]. Journal of Management Sciences in China202225(8): 45-62.
[13] Deerwester S, Dumais S T, Furnas G W, et al. Indexing by latent semantic analysis[J]. Journal of the American Society for Information Science199041(6): 391-407.
[14] Hofmann T. Unsupervised learning by probabilistic latent semantic analysis[J]. Machine Learning200142(1): 177-196.
[15] Blei D M, Ng A Y, Jordan M I. Latent dirichlet allocation[J]. Journal of Machine Learning Research20033(4-5): 993-1022.
[16] 关鹏, 王曰芬. 科技情报分析中LDA主题模型最优主题数确定方法研究[J]. 现代图书情报技术2016(9): 42-50.
  Guan P, Wang Y F. Identifying optimal topic numbers from sci-tech information with LDA model[J]. New Technology of Library and Information Service2016(9): 42-50.
[17] 徐戈, 王厚峰. 自然语言处理中主题模型的发展[J]. 计算机学报201134(8): 1423-1436.
  Xu G, Wang H F. The development of topic models in natural language processing[J]. Chinese Journal of Computers201134(8): 1423-1436.
[18] Sutherland I, Kiatkawsin K. Determinants of guest experience in airbnb: A topic modeling approach using LDA[J]. Sustainability202012(8): 3402.
[19] 杨梦婷, 熊回香, 肖兵, 等. 基于动态特征的学者推荐研究[J]. 情报理论与实践202245(4): 120-127.
  Yang M T, Xiong H X, Xiao B, et al. Research on scholar recommendation based on dynamic features[J]. Information Studies(Theory & Application)202245(4): 120-127.
[20] 王伟, 高宁, 徐玉婷, 等. 基于LDA的众筹项目在线评论主题动态演化分析[J]. 数据分析与知识发现20215(10): 103-123.
  Wang W, Gao N, Xu Y T, et al. Topic evolution of online reviews for crowdfunding campaigns[J]. Data Analysis and Knowledge Discovery20215(10): 103-123.
[21] Zhang F G, Xue B Y, Li Y R, et al. Effect of textual features on the success of medical crowdfunding: Model development and econometric analysis from the tencent charity platform[J].Journal of Medical Internet Research202123(6): e22395.
[22] Wu Y, Zhang X, Xiao Q. Appeal to the head and heart: The persuasive effects of medical crowdfunding charitable appeals on willingness to donate[J]. Information Processing & Management202259(1): 102792.
[23] 王伟, 赵勇勇, 王洪伟, 等. 投资者经验对在线融资项目融资绩效的影响: 未来流行度和项目声望的中介作用[J]. 中国管理科学202331(8): 9-21.
  Wang W, Zhao Y Y, Wang H W, et al. Impact of investor experience on online financing project's financial performance: Mediating role of future popularity and reputation[J]. Chinese Journal of Management Science202331(8): 9-21.
[24] 王伟, 陈伟, Zhu Kevin, 等. 众筹融资成功率与语言风格的说服性——基于Kickstarter的实证研究[J]. 管理世界2016(5): 81-98.
  Wang W, Chen W, Zhu K, et al. Crowdfunding success and language persuasiveness: Based on the empirical analysis of Kickstarter[J].Journal of Management World2016(5): 81-98.
[25] 齐托托, 刘倩, 王天梅,等. 知识付费产品描述语言风格的说服效应研究——知识生产者声誉的调节作用[J]. 南开管理评论202023(5): 159-170.
  Qi T T, Liu Q, Wang T M, et al. The persuasive effect of linguistic styles in the description of paying for knowledge product: The moderating effect of knowledge producer's reputation[J]. Nankai Business Review202023(5): 159-170.
[26] Parhankangas A, Renko M. Linguistic style and crowdfunding success among social and commercial entrepreneurs[J]. Journal of Business Venturing201732(2): 215-236.
[27] Jin P Y. Medical crowdfunding in China: Empirics and ethics[J]. Journal of Medical Ethics201945(8): 538-544.
[28] Xu K B, Wang X Y. “Kindhearted people, please save my family”: Narrative strategies for new media medical crowdfunding[J]. Health Communication202035(13): 1605-1613.
[29] Jiang C X, Han R R, Xu Q F, et al. The impact of soft information extracted from descriptive text on crowdfunding performance[J].Electronic Commerce Research and Applications202043: 101002.
[30] 王伟, 何翎, Zhu Kevin, 等. 更新信号的阶段性融资效应: 基于众筹市场的跨类别实证研究[J]. 中国管理科学202028(11): 155-166.
  Wang W, He L, Zhu K, et al. The periodic impact of linguistic cues to update signalson successful crowdfunding campaigns among categories[J]. Chinese Journal of Management Science202028(11): 155-166.
[31] Brahnam S. Building character for artificial conversational agents: Ethos, ethics, believability, and credibility[J]. PsychNology Journal20097(1): 9-47.
[32] 曹京渊. 亚里士多德的实用修辞观[J]. 兰州大学学报200129(2): 144-148.
  Cao J Y. On Aristotelian practical rhetoric[J]. Journal of Lanzhor University200129(2): 144-148.
[33] Tirdatov I. Web-based crowd funding: Rhetoric of success[J]. Technical Communication201461(1): 3-24.
[34] 武帅, 施奕, 杨秀璋, 等. 基于社交网络分析和LDA主题挖掘的短文本挖掘研究[J]. 现代电子技术202245(20): 124-128.
  Wu S, Shi Y, Yang X Z, et al. Research on short text mining based on social network analysis and LDA topic mining[J]. Modern Electronics Technique202245(20): 124-128.
[35] Paulus T M, Roberts K R. Crowdfunding a “real-life superhero”: The construction of worthy bodies in medical campaign narratives[J]. Discourse, Context & Media, 201821: 64-72.
[36] Berliner L S, Kenworthy N J. Producing a worthy illness: Personal crowdfunding amidst financial crisis[J]. Social Science & Medicine2017187: 233-242.
[37] Vassell A, Crooks V A, Snyder J. What was lost, missing, sought and hoped for: Qualitatively exploring medical crowdfunding campaign narratives for Lyme disease[J]. Health202125(6): 707-721.
[38] Nguyen H, Calantone R, Krishnan R. Influence of social media emotional word of mouth on institutional investors’ decisions and firm value[J]. Management Science201966(2): 887-910.
[39] Leslie L L, Ramey G. Donor behavior and voluntary support for higher education institutions[J]. The Journal of Higher Education198859(2): 115-132.
[40] 高阳. 社群公益众筹的个人感知对捐赠意愿的影响研究[D]. 哈尔滨: 哈尔滨工业大学博士学位论文, 2018.
  Gao Y. Research on the impact of individual perception of community donation-based crowdfunity on donation intention[D]. Harbin: Doctoral Dissertation of Harbin Institute of Technology, 2018.
[41] Kaminski J C, Hopp C. Predicting outcomes in crowdfunding campaigns with textual, visual, and linguistic signals[J]. Small Business Economics202055(3): 627-649.
[42] 张建羽, 位倩, 王澜, 等. 媒体关注度对股票波动率的影响研究[J]. 中国市场2017(29): 63-66.
  Zhang J Y, Wei Q, Wang L, et al. A study on the impact of media attention on stock price volatility[J]. China Market2017(29): 63-66.
[43] Kahneman D. Attention and effort[M]. Englewood Cliffs: Prentice-Hall, 1973.
[44] 刘畅, 陈守明. 文本信息含量与公益众筹绩效研究——基于有限注意的视角[J]. 投资研究202241(6): 96-113.
  Liu C, Chen S M. Text information content and public welfare crowdfunding performance: From the perspective of limited attention[J]. Review of Investment Studies202241(6): 96-113.
[45] Simon H A. A behavioral model of rational choice[J]. The Quarterly Journal of Economics195569(1): 99-118.
[46] Zhang Y X, Du Y J, Li Y. Entertainment apps, limited attention and investment performance[J]. Frontiers in Psychology202314: 1118797.
[47] Li L Q, Yang L, Zhao M, et al. Exploring the success determinants of crowdfunding for cultural and creative projects: An empirical study based on signal theory[J]. Technology in Society202270: 102036.
[48] Zheng H C, Li D H, Wu J, et al. The role of multidimensional social capital in crowdfunding: A comparative study in China and US[J]. Information & Management201451(4): 488-496.
[49] 蒋志强, 王逸明, 汪鹏, 等 .亲社会行为机理可以促进医疗众筹项目筹资吗?——基于轻松筹的实证研究[J]. 中国管理科学202432(4): 227-236.
  Jiang Z Q, Wang Y M, Wang P, et al. Do factors driving prosocial behaviors promote fundraising in medical crowdfunding?Evidence from Qingsong Chou[J]. Chinese Journal of Management Science202432(4): 227-236.
[50] Petty R E, Cacioppo J T. The elaboration likelihood model of persuasion[J]. Advances in Experimental Social Psychology198619: 123-205.
[51] Glanzer M, Cunitz A R. Two storage mechanisms in free recall[J]. Journal of Verbal Learning and Verbal Behavior19665(4): 351-360.
文章导航

/