[目的/意义] 为了丰富社交互动行为和知识付费行为的理论研究，有效识别潜在知识付费用户，从而提高在线知识社区的变现能力，在总结前人研究结论的基础上，研究不同类型以及不同程度的交互行为对于预测知识付费用户的贡献度及其变化趋势。[方法/过程] 以从知乎社区（www.zhihu.com）爬取的400万用户社会交互行为数据为依托，根据交互主体和交互方向的不同对该社区的用户社会交互行为进行分类，然后，利用随机森林算法研究不同类型和不同程度的交互行为对知识付费用户预测的贡献程度，并对结果进行分析比较。[结果/结论] 结果发现，用户和其他用户的交互影响大于用户和平台交互的影响，特别是，用户对其他用户的主动交互行为的影响大于用户接收到的来自其他用户的交互行为的影响。此外，在一定的阈值内，社交互动的程度越大，其对知识付费行为预测的贡献越大。不同的交互类型具有不同的阈值，但是超过这个阈值以后，关系则不再是简单的单调增加关系，可能趋于平缓甚至显著下降。
[Purpose/significance] In order to enrich the theoretical study between social interaction behavior and knowledge payment behavior, identify potential paying customers effectively so as to improve the marketability of online knowledge community, this paper studies the contribution degree of different types and degrees of interactive behaviors to the prediction of knowledge paying users and their changing trends on the basis of summarizing the predecessors’ research conclusion. [Method/process] Based on the social interaction behavior data of 4 million users crawled from the Zhihu community (www.zhihu.com), this paper classified the social interaction behavior of users in the community according to the different interaction subjects and interaction directions, and then used random forest algorithm studied the contribution of different types and degrees of interaction behavior to the prediction of knowledge paying users. [Result/conclusion] The results show that the impact of the interaction between users and other users is greater than that of the interaction between users and the platform. In particular, the impact of active interactions sent to other users is greater than the impact of passive interactions from other users. In addition, within a certain threshold, the greater the degree of social interaction, the greater its contribution to the prediction of knowledge payment behavior. Different interaction types have different thresholds, but beyond this threshold, the relationship is no longer a simple monotonic increase and may tend to be flat or even significantly lower.
[1] 中国互联网协会分享经济工作委员会国家信息中心分享经济研究中心. 中国分享经济发展报告2017[EB/OL].[2019-08-26].http://www.sic.gov.cn/archiver/SIC/UpFile/Files/Htmleditor/201703/20170302125144221.pdf.
[2] LI G. Exploring users' motivation to contribute in online platforms[EB/OL].[2019-08-26].http://laitinej.mbnet.fi/jouni/Artikkelit/DC_paper_4.pdf.
[3] NG C S P. Intention to purchase on social commerce websites across cultures:A cross-regional study[J]. Information & management, 2013, 50(8):609-620.
[4] 周涛, 檀齐. 基于社会资本理论的知识付费用户行为机理研究[J]. 现代情报, 2017(11):48-52.
[5] 李武. 在线知识付费平台:何去何从?[J]. 图书情报知识, 2018, 183(3):2.
[6] ZHAO Y, LIU Z, SONG S. Why should I pay for the knowledge in social Q&A platforms?[C]//International conference on information.The United Kingdom:Springer, Cham, 2018:577-582.
[7] DENG S, TONG J, LIN Y, et al. Motivating scholars' responses in academic social networking sites:an empirical study on ResearchGate Q&A behavior[J]. Information processing & management,2019, 56(6):102082.
[8] SCHOEN H, GAYO-AVELLO D, TAKIS METAXAS P, et al. The power of prediction with social media[J]. Internet research, 2013, 23(5):528-543.
[9] CHEN C C, LIN Y C. What drives live-stream usage intention? the perspectives of flow, entertainment, social interaction, and endorsement[J]. Telematics and informatics, 2018, 35(1):293-303.
[10] BLAZEVIC V, WIERTZ C, COTTE J, et al. GOSIP in cyberspace:conceptualization and scale development for general online social interaction propensity[J]. Journal of interactive marketing, 2014, 28(2):87-100.
[11] ALLEB S M, CHORLEY M J, COLOMBO G B, et al. Exploiting user interest similarity and social links for micro-blog forwarding in mobile opportunistic networks[J]. Pervasive and mobile computing, 2014, 11:106-131.
[12] LU X, YU Z, GUO B, et al. Predicting the content dissemination trends by repost behavior modeling in mobile social networks[J]. Journal of network and computer applications, 2014, 42:197-207.
[13] STORRS G. A conceptualisation of multiparty interaction[J]. Interacting with computers, 1994, 6(2):173-189.
[14] LIU X, FENG J. Research on the influencing factors of the willingness to pay for knowledge consumers in the knowledge payment platform[EB/OL].[2019-08-27]. https://aisel.aisnet.org/cgi/viewcontent.cgi?article=1016&=&context=whiceb2018&=&sei-redir=1.
[15] CAI S, LUO Q F, FU X, et al. Paying for Knowledge:Why people paying for live broadcasts in online knowledge sharing community?[EB/OL].[2019-08-27]. https://aisel.aisnet.org/pacis2018/286.
[16] CAI S, LUO Q, FU X, et al. Paying for live broadcast:predicting internet knowledge product sharing[EB/OL].[2019-08-27]. https://pdfs.semanticscholar.org/ab6b/210302138823e79b39e30 a118a50f1fadec5.pdf.
[17] 张帅, 王文韬, 李晶. 用户在线知识付费行为影响因素研究[J]. 图书情报工作, 2017,61(10):94-100.
[18] 李钢, 卢艳强, 滕树元. 用户在线知识付费行为研究——基于计划行为理论[J]. 图书馆学研究, 2018, 429(10):39-50.
[19] BOCK G W, ZMUD R W, KIM Y G, et al. Behavioral intention formation in knowledge sharing:examining the roles of extrinsic motivators, social-psychological factors, and organizational climate[J]. MIS quarterly, 2005, 29(1):87-111.
[20] LEE Y, KWON O. Intimacy, familiarity and continuance intention:an extended expectation-confirmation model in web-based services[J]. Electronic commerce research and applications,2011,10(3):342-57.
[21] SHIN J K, PARK M, JU Y. The effect of the online social network structure characteristics on network involvement and consumer purchasing intention:focus on Korean social promotion sites[C]//The 11th International DSI and the 16th APDSI Joint Meeting, Taipei:Asia Pacific Decision Sciences Institute,2011.
[22] WU H L, WANG J W. An empirical study of flow experiences in social network sites[EB/OL].[2019-08-27]. https://aisel.aisnet.org/pacis2011/215.
[23] ZHANG Y, Pennacchiotti M. Predicting purchase behaviors from social media[C]//Proceedings of the 22nd international conference on World Wide Web. Brazil:ACM, 2013:1521-1532.
[24] 徐少成, 李东喜. 基于随机森林的加权特征选择算法[J].统计与决策, 2018(18):25-8.
[25] 姚登举, 杨静, 詹晓娟. 基于随机森林的特征选择算法[J]. 吉林大学学报(工学版),2014,44(1):137-141.
[26] 周涛,檀齐, BAYAN T,等.社会交互对用户知识付费意愿的作用机理研究[J].图书情报工作, 2019(4):94-100.
[27] WANG J J. A research on the development trend of knowledge payment based on Zhihu. I[M].//LI Zhiqing. The new silk roadlLeads through the Arab peninsula:mastering global business and innovation. Bingley:Emerald Publishing Limited,2019:229-241.
[28] 李武,艾鹏亚,许耀心.在线付费问答平台的用户付费模式及付费意愿研究[J].图书情报工作,2018,62(13):24-29.
[29] 吴楠. 从知乎Live看知识付费[J]. 传播力研究, 2019, 3(4):217.
