Prediction and Analysis of Social Influence for Crowdfunding Projects

doi:10.7652/xjtuxb201704014

您当前的位置：

首页 >

文章列表页 >

Prediction and Analysis of Social Influence for Crowdfunding Projects

更新时间：2025-07-09

- Prediction and Analysis of Social Influence for Crowdfunding Projects
- Vol. 51, Issue 4, Pages: 91-96(2017)
- 作者机构：
  
  北京大学信息科学技术学院,北京,100871
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201704014
  CLC： TP391.9
- Online First：10 April 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
Prediction and Analysis of Social Influence for Crowdfunding Projects[J]. 2017, 51(4): 91-96.
DOI：

Prediction and Analysis of Social Influence for Crowdfunding Projects[J]. 2017, 51(4): 91-96. DOI： 10.7652/xjtuxb201704014.

摘要

针对众筹项目由于社会影响力不足而成功率较低的问题

提出了面向众筹平台的社交网络影响力预测方法。该方法基于众筹网站和社交网络的实时观测数据

分别提取累积和增量等多类别预测特征

并随着社会推广的进行而渐进地预测项目的社交网络影响力增益

最后采用带L1一范数约束惩罚的逻辑回归等方法进行预测特征分析。实验结果表明:在整个推广过程中

众筹项目的社交网络影响力可以被精确预测

准确率最高达88.31%; 分类器在采用累积特征时具有比采用增量特征更好的预测效果; 项目统计特征和推广者的社会影响力等特征具有更高的重要性和更稳定的显著性。该方法成功地解决了众筹项目的社会影响力预测问题

并为设计更好的社交网络推广策略提供了依据。

Abstract

A novel influence prediction method is proposed to deal with the social promotion problem on crowdfunding platforms and to investigate the predictability of social influence for fundraising projects. The proposed method gradually predicts future influence growth of each project based on features extracted in different timestamps from data streams of crowdfunding websites and social networks. Experimental results show that features extracted from aggregate data rather than incremental data are better indicators of the social influence growth

and the method has the highest prediction precision 88.31%. Analysis of features also shows that some features such as the statistic of projects and social influence of promoters are consistently significant within the prediction process. These results provide hints for devising better social promotions.

关键词

Keywords

references

AN Jisun, QUERCIA D, CROWCROFT J. Recommending investors for crowdfunding projects [C]∥Proceedings of the 23rd International Conference on World Wide Web. New York, USA: ACM, 2014: 261-270.

RAKESH V, CHOO J, REDDY C K. Project recommendation using heterogeneous traits in crowdfunding [C]∥Proceedings of the 9th International AAAI Conference on Web and Social Media. Palo Alto, CA, USA: AAAI Press, 2015: 337-346.

RAKESH V, LEE W C, REDDY C K. Probabilistic group recommendation model for crowdfunding domains [C]∥Proceedings of the 9th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2016: 257-266.

LU C T, XIE Sihong, KONG Xiangnan, et al. Inferring the impacts of social media on crowdfunding [C]∥Proceedings of the 7th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2014: 573-582.

LI Yan, RAKESH V, REDDY C K. Project success prediction in crowdfunding environments [C]∥Proceedings of the 9th ACM International Conference on Web Search and Data Mining. New York, USA: ACM, 2016: 247-256.

李雅婷, 左文明. 众筹项目筹资结果预测模型 [J]. 统计与决策, 2016(2): 86-89.

LI Yating, ZUO Wenming. Results prediction of crowdfunding projects [J]. Statistics and Decision, 2016(2): 86-89.

HUI J S, GERBER E M, GERGLE D. Understanding and leveraging social networks for crowdfunding: opportunities and challenges [C]∥Proceedings of the 2014 Conference on Designing Interactive Systems. New York, USA: ACM, 2014: 677-680.

CHENG J, ADAMIC L, DOW P A, et al. Can cascades be predicted? [C]∥Proceedings of the 23rd International Conference on World Wide Web. New York, USA: ACM, 2014: 925-936.

WANG Senzhang, YAN Zhao, HU Xia, et al. Burst time prediction in cascades [C]∥Proceedings of the 9th International AAAI Conference on Web and Social Media. Palo Alto, CA, USA: AAAI Press, 2015: 325-331.

TANG Jie, SUN Jimeng, WANG Chi, et al. Social influence analysis in large-scale networks [C]∥Proceedings of the 15th ACM Sigkdd International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2009: 807-816.

张磊,马春光,杨松涛,等.面向路网环境速度预测攻击的隐私保护.2017,51(2):27-32.[doi:10.7652/xjtuxb201702005]

李晓娟,孙文磊,袁逸萍,等.扰动环境下作业车间网络多瓶颈识别方法研究.2016,50(12):64-72.[doi:10.7652/xjtuxb 201612011]

谈博,蔡远利,史椸.采用变时域监督预测控制的机炉协调控制方法.2016,50(12):92-98.[doi:10.7652/xjtuxb201612 015]

杨沫,由磊,李冰,等.采用传递概率与社会网络分析的延迟容忍网络路由.2016,50(12):136-141.[doi:10.7652/xjtuxb 201612021]

李扬,潘泉,杨涛.基于短文本情感分析的敏感信息识别.2016,50(9):80-84.[doi:10.7652/xjtuxb201609013]

王菲菲,杨扬,蒋飞,等.面向用户话题相似性特征的链路预测方法.2016,50(8):103-109.[doi:10.7652/xjtuxb201608 017]

魏倩,蔡远利.一种基于神经网络的中制导改进算法.2016,50(7):125-130.[doi:10.7652/xjtuxb201607019]

赵辉,郑庆华,张未展.多版本视频点播流媒体服务器集群资源分配方法.2016,50(6):30-35.[doi:10.7652/xjtuxb201606 005]

刘兆丽,秦涛,管晓宏,等.采用用户名相似度传播模型的线上用户身份.2016,50(4):1-6.[doi:10.7652/xjtuxb201604 001]

孟宪佳,马建峰,王一川.面向社交网络中多背景的信任评估模型.2015,49(4):73-77.[doi:10.7652/xjtuxb201504012]

叶娜,赵银亮,边根庆,等.模式无关的社交网络用户识别算法.2013,47(12):19-25.[doi:10.7652/xjtuxb201312004]

张赛,徐恪,李海涛.微博类社交网络中信息传播的测量与分析.2013,47(2):124-130.[doi:10.7652/xjtuxb201302021]

莫同,褚伟杰,李伟平,等.采用超图的微博群落感知方法.2012,46(11):120-126.[doi:10.7652/xjtuxb201211022]

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Integrated and Joint Design Optimization of Centrifugal Compressor Impeller and Casing Treatment at Multiple Working Points

Knowledge Graph Representation Learning Driven by Semantic Discrimination and Subgraph Integration

Bi-Level Multi-Obj ective Optimization of a Wind-Solar Coupled Hydrogen Production System Based on the Synergy of Hybrid Electrolyzer Arrays

Review of the Application of EBSILON Software in Combined Heat and Power System Optimization

Research on the Electrohydrodynamic Effects of Ionic Liquid-Modified Fuels

Related Author

No data

Related Institution

No data

⁰