基于CLV偏好挖掘模型的数字社区用户偏好挖掘研究

doi:10.13998/j.cnki.issn1002-1248.23-0084

摘要/Abstract

摘要： [目的/意义]数字社区已经成为企业高效管理用户的一种方式,用户行为信息以及用户的客户生命周期价值对数字社区的用户偏好挖掘具有重要意义。且现有的数字社区研究缺乏对用户价值和未来偏好挖掘的研究。[方法/过程]针对数字社区的用户群体,本文提出基于客户生命周期价值CLV（Customer Lifetime Value,CLV）的偏好挖掘模型CLV-PM（CLV-Preference Mining,CLV-PM）。首先,为反映用户真实偏好,基于用户行为信息,借助RFM模型和K-Means++算法挖掘用户群体特征,生成用户价值类别标签;其次,为考虑用户时序性和差异性以及增强模型对偏好的认知,利用用户CLV构建用户-评分矩阵,并借助协同过滤算法挖掘用户预测偏好;最后,绘制数字社区目标用户的用户偏好画像。[结果/结论]“微信社群”管理平台的用户数据集中,可划分为重要价值用户、低价值用户、回流用户和重要挽留用户4种用户价值类别;目标用户16254为重要价值用户,采取“留存和维持”为主的运营策略;历史偏好为欢乐跳一跳、秒杀等活动,预测偏好为飞行棋大作战、猜码图等活动,目标用户偏好画像为数字社区运营和维护用户提供依据。

关键词: CLV-PM, 协同过滤, 数字社区, 用户偏好, 信息行为

Abstract: [Purpose/Significance] Digital communities have become a way for enterprises to manage users efficiently. The existing research on digital community rarely considers the importance of user behavior information and user's customer life cycle value to the mining of user preferences in digital community. This research aims to give full play to the digital community's characteristics such as intuitive, convenient, interesting, and interactive properties so that the research results can benefit every user in their use of the digital community and every enterprise in their user management. [Method/Process] Aiming at the user groups in digital community, this paper proposes a preference mining model ClV-Preference mining (CLV-PM) based on Customer Lifetime Value (CLV). First, in order to reflect the real preferences of users, the three indicators of the RFM model are used to quantify user behavior information, and the group characteristics of users are mined through K-mean ++ algorithm to generate user value category labels. Second, in order to consider the timeliness and difference of users and enhance the model's cognition of preferences, this paper uses the entropy weight method to solve the indicator weights of each activity, obtains user CLV to construct user-project scoring matrix, and uses the collaborative filtering algorithm to predict user preferences. Finally, based on the user value category, user historical preference and user forecast preference, the user preference profile of target users in digital community is generated, and feasible suggestions are put forward for the operation and maintenance of target users according to the user preference profile. [Results/Conclusions] The user dataset of the "Wechat community" management platform can be divided into four user value categories: important value users, low value users, returned users and important retention users. Target users 16254 are important value users, and the operation strategy of "retention and maintenance" is adopted. The historical preferences are happy hop, sec-kill and other activities; the prediction preference is flying chess battle, guessing code map and other activities; the target user preference sketch provides the basis for the operation and maintenance of users in the digital community. In terms of data source, the CLV-PM model proposed in this paper directly reflects user preferences based on user behavior information and reduces the problem of score distortion. To provide a new perspective for the research of user behavior in digital community, the construction of user-project scoring matrix based on user CLV fully considers the user value of digital community and provides a new direction for the extension and application of CLV. However, due to limited research space, this paper did not conduct model evaluation research on the proposed model, which can be further discussed in subsequent studies.

Key words: CLV-PM, collaborative filtering, digital community, user preference, information behavior

中图分类号:

G250

肖耘, 许欢欢, 肖雅元, 赵又霖, 庞航远. 基于CLV偏好挖掘模型的数字社区用户偏好挖掘研究[J]. 农业图书情报学报, 2023, 35(2): 45-60.

XIAO Yun, XU Huanhuan, XIAO Yayuan, ZHAO Youlin, PANG Hangyuan. User Preference Mining in Digital Community Based on CLV Preference Mining Model[J]. Journal of Library and Information Science in Agriculture, 2023, 35(2): 45-60.

参考文献

[1] GOLDBERG D, NICHOLS D, OKI B M, et al.Using collaborative filtering to weave an information tapestry[J]. Communications of the ACM, 1992, 35(12): 61-70.
[2] RAJKUMAR V, KUMAR V.A customer lifetime value framework for customer selection and resource allocation strategy[J]. Journal of marketing, 2004, 68(4): 106-125.
[3] KUMAR V, VENKATESAN R, RAJAN B.Implementing profitability through a customer lifetime value management framework[J]. GfK marketing intelligence review, 2014, 1(2): 32-43.
[4] 李玉婷, 张琅, 姚吉呈. 车险客户生命周期价值研究[J]. 保险研究, 2016(8): 100-114.
LI Y T, ZHANG L, YAO J C.The research on customer lifetime value of auto insurance[J]. Insurance studies, 2016(8): 100-114.
[5] 齐佳音, 马君, 肖丽妍, 等. 考虑客户风险修正的客户终生价值建模[J]. 管理工程学报, 2015, 29(2): 149-159.
QI J Y, MA J, XIAO L Y, et al.Risk-adjusted customer lifetime value measurement[J]. Journal of industrial engineering and engi-neering management, 2015, 29(2): 149-159.
[6] 朱至文, 周浩东, 孙家溪. 基于客户网络影响力的网络口碑价值度量与预测方法[J]. 统计与决策, 2021, 37(7): 166-169.
ZHU Z W, ZHOU H D, SUN J X.Measurement and prediction method of online word-of-mouth value based on customer's network influence[J]. Statistics & decision, 2021, 37(7): 166-169.
[7] 陈少霞. 基于价值结构的顾客赢利性测量与管理[J]. 管理工程学报, 2017, 31(2): 109-118.
CHEN S X.The measurement and management of customer profitability: Based on value structure[J]. Journal of industrial engineering and engineering management, 2017, 31(2): 109-118.
[8] 余佳琪, 赵豆豆, 刘蕤. 在线健康社区慢性病患者评论主题情感协同挖掘研究——以甜蜜家园为例[J/OL]. 数据分析与知识发现: 1-20[2023-03-30]. http://kns.cnki.net/kcms/detail/10.1478.G2.20230224.1142.002.html.
YU J Q, ZHAO D D, LIU R. A topic-sentiment collaborative data Mining on the chronic disease patients' reviews in online health community - An evidence from "sweet homeland"[J/OL]. Data analysis and knowledge discovery: 1-20[2023-03-30]. http://kns.cnki.net/kcms/detail/10.1478.G2.20230224.1142.002.html.
[9] 单思远, 易明. 在线健康社区用户自我信息披露意愿研究[J]. 图书情报工作, 2022, 66(21): 67-77.
SHAN S Y, YI M.Research on self-disclosure intention of online health community users[J]. Library and information service, 2022, 66(21): 67-77.
[10] 肖雪, 李敏, 秦馨怡, 等. 虚拟阅读社区用户互动特征与影响因素[J/OL]. 图书馆论坛: 1-11[2023-03-30]. http://kns.cnki.net/kcms/detail/44.1306.G2.20221116.1232.002.html.
XIAO X, LI M, QIN X Y, et al. Research on users' interaction characteristics and influencing factors in virtual reading community[J/OL]. Library tribune: 1-11[2023-03-30].http://kns.cnki.net/kcms/detail/44.1306.G2.20221116.1232.002.html.
[11] 普哲缘, 李胜利. 视频评论特征对观众评论行为的影响——以哔哩哔哩为例[J]. 图书情报工作, 2022, 66(20): 130-140.
PU Z Y, LI S L.Influence of video comments characteristics on viewers' commenting behaviors - Taking bilibili as an example[J]. Library and information service, 2022, 66(20): 130-140.
[12] 付少雄, 朱梦蝶, 郑德俊, 等. 基于社会资本理论的在线医疗社区医生知识贡献行为动因研究[J]. 情报资料工作, 2022, 43(3): 67-74.
FU S X, ZHU M D, ZHENG D J, et al.Research on the behavior motivation of doctors' knowledge contribution in online medical community based on social capital theory[J]. Information and documentation services, 2022, 43(3): 67-74.
[13] 赵雪芹, 王青青, 蔡铨. 基于三元交互决定论的在线学术社区动态知识推荐服务模型研究[J]. 农业图书情报学报, 2021, 33(5): 4-13.
ZHAO X Q, WANG Q Q, CAI Q.Dynamic knowledge recommendation service model of online academic community based on ternary interactive determinism[J]. Journal of library and information science in agriculture, 2021, 33(5): 4-13.
[14] 王盼盼, 吴志艳, 罗继锋. 有偿奖励对医生在线健康社区中贡献行为的影响[J]. 系统管理学报, 2022, 31(2): 343-352.
WANG P P, WU Z Y, LUO J F.Effect of monetary incentive on physicians' contribution behavior in online healthcare community[J]. Journal of systems & management, 2022, 31(2): 343-352.
[15] 潘涛涛, 吕英杰. 在线健康社区中基于SOR模型的用户参与行为影响因素研究[J]. 情报资料工作, 2022, 43(2): 76-83.
PAN T T, LU Y J.Research on influencing factors of user participation behavior based on SOR model in online health community[J]. Information and documentation services, 2022, 43(2): 76-83.
[16] 赵欣, 李佳倩, 赵琳, 等. 在线社区的知识增殖: 用户行为与用户信任的互惠关系研究[J]. 现代情报, 2020, 40(10): 84-92.
ZHAO X, LI J Q, ZHAO L, et al.Knowledge proliferation in online communities: A research on reciprocal causality between user behavior and user trust[J]. Journal of modern information, 2020, 40(10): 84-92.
[17] 周涛, 王盈颖, 邓胜利. 基于社会资本理论的在线健康社区用户参与行为研究[J]. 信息资源管理学报, 2020, 10(2): 59-67, 129.
ZHOU T, WANG Y Y, DENG S L.Research on online health community users' participation based on social capital theory[J]. Journal of information resources management, 2020, 10(2): 59-67, 129.
[18] 陈星, 张星, 肖泉. 在线健康社区的用户持续知识分享意愿研究——一个集成社会支持与承诺—信任理论的模型[J]. 现代情报, 2019, 39(11): 55-68.
CHEN X, ZHANG X, XIAO Q.Understanding continuous knowledge sharing in the online health communities - An integrated model of social support theory and commitment-trust theory[J]. Journal of modern information, 2019, 39(11): 55-68.
[19] 吴江, 刘涛, 刘洋. 在线社区用户画像及自我呈现主题挖掘——以网易云音乐社区为例[J]. 数据分析与知识发现, 2022, 6(7): 56-69.
WU J, LIU T, LIU Y.Mining online user profiles and self-presen-tations: Case study of NetEase music community[J]. Data analysis and knowledge discovery, 2022, 6(7): 56-69.
[20] 张军, 李新旺, 李鹏. 多维属性融合视角下的在线健康社区关键用户识别研究[J]. 情报科学, 2022, 40(3): 82-90.
ZHANG J, LI X W, LI P.Key user identification of online health community based on multi-dimensional attribute fusion[J]. Information science, 2022, 40(3): 82-90.
[21] 王帅. 突发公共卫生事件情境下在线健康社区用户画像与分群研究[J]. 情报科学, 2022, 40(6): 98-107.
WANG S.Study on user portrait and clustering of online health community in the context of public health emergencies[J]. Informa-tion science, 2022, 40(6): 98-107.
[22] 朱益平, 朱怡, 张诚. 情感体验维度下在线健康社区用户参与行为影响因素研究[J]. 农业图书情报学报, 2022, 34(10): 15-18.
ZHU Y P, ZHU Y, ZHANG C.Influencing factors of user participation behavior in online health community under the dimension of emotional experience[J]. Journal of library and information science in agriculture, 2022, 34(10): 15-18.
[23] 钱宇星, 周华阳, 周利琴, 等. 老年在线社区用户健康信息需求挖掘研究[J]. 现代情报, 2019, 39(6): 59-69.
QIAN Y X, ZHOU H Y, ZHOU L Q, et al.Mining users' health information needs in senior online community[J]. Journal of modern information, 2019, 39(6): 59-69.
[24] 成全, 郑抒琳. 在线健康社区用户信息需求的层级多标签分类研究[J]. 情报理论与实践, 2023, 46(2): 100-108.
CHENG Q, ZHENG S L.Research on hierarchical multi-label classification of user information demand in online health community[J]. Information studies: Theory & application, 2023, 46(2): 100-108.
[25] ADOMAVICIUS G, TUZHILIN A.Toward the next generation of recommender systems: A survey of the state-of-the-art and possi-ble extensions[J]. IEEE transactions on knowledge and data engi-neering, 2005, 17: 734-749.
[26] 宋凯, 冉从敬. 基于企业画像的高校专利个性化推荐[J]. 图书馆论坛, 2022, 42(9): 123-131.
SONG K, RAN C J.Personalized recommendation of university patents based on enterprise portraits[J]. Library tribune, 2022, 42(9): 123-131.
[27] 单晓红, 崔凤艳, 刘晓燕. 融合话题多维特征和用户兴趣偏好的微博话题推荐研究[J]. 现代情报, 2022, 42(5): 69-76, 97.
SHAN X H, CUI F Y, LIU X Y.Research on microblog topic recommendation integrating topic multidimensional features and user interest preferences[J]. Journal of modern information, 2022, 42(5): 69-76, 97.
[28] 李亚梅, 秦春秀, 马续补. 基于科研人员情境化主题偏好的科技文献协同推荐研究[J]. 情报理论与实践, 2021, 44(12): 180-189.
LI Y M, QIN C X, MA X B.Research on collaborative recommenda-tion of scientific and technological literature based on researchers' contextual topic preference[J]. Information studies: Theory & appli-cation, 2021, 44(12): 180-189.
[29] 李宝. 基于用户画像的高校图书馆个性化资源推荐服务设计[J]. 新世纪图书馆, 2021(4): 68-75.
LI B.Design on personalized resources recommendation service of university library based on user portrait[J]. New century library, 2021(4): 68-75.
[30] 杨辰, 陈晓虹, 王楚涵, 等. 基于用户细粒度属性偏好聚类的推荐策略[J]. 数据分析与知识发现, 2021, 5(10): 94-102.
YANG C, CHEN X H, WANG C H, et al.Recommendation strategy based on users' preferences for fine-grained attributes[J]. Data analysis and knowledge discovery, 2021, 5(10): 94-102.
[31] 李浩, 余雪, 杜旭, 等. 基于学习者时空特征的移动学习资源推荐模型研究[J]. 现代教育技术, 2020, 30(10): 13-19.
LI H, YU X, DU X, et al.Research on the mobile learning resource recommendation model based on learners' temporal and spatial characteristics[J]. Modern educational technology, 2020, 30(10): 13-19.
[32] LI R.Simulation research of university library recommended system based on big data and data mining[C] //Proceedings of the 2015 3rd international conference on machinery, materials and information technology applications, advances in computer science research. Paris, France: Atlantis Press, 2015: 202-206.
[33] 邢玲, 宋章浩, 马强. 基于混合行为兴趣度的用户兴趣模型[J]. 计算机应用研究, 2016, 33(3): 661-664, 668.
XING L, SONG Z H, MA Q.User interest model based on hybrid behaviors interest rate[J]. Application research of computers, 2016, 33(3): 661-664, 668.
[34] 李建廷, 郭晔, 汤志军. 基于用户浏览行为分析的用户兴趣度计算[J]. 计算机工程与设计, 2012, 33(3): 968-972.
LI J T, GUO Y, TANG Z J.User interest degree calculating based on analysis users' browsing behaviors[J]. Computer engineering and design, 2012, 33(3): 968-972.
[35] JACKSON R, WANG P.Strategic database marketing[M]. Lincolnwood, Ill, USA: NTC Business Books, 1994.
[36] BULT J R, WANSBEEK T.Optimal selection for direct mail[J]. Marketing science, 1995, 14(4): 378-394.
[37] SHIH F Y, WU Y T.Three-dimensional euclidean distance trans-formation and its application to shortest path planning[J]. Pattern recognition, 2004, 37(1): 79-92.
[38] 吴广建, 章剑林, 袁丁. 基于K-means的手肘法自动获取K值方法研究[J]. 软件, 2019, 40(5): 167-170.
WU G J, ZHANG J L, YUAN D.Automatically obtaining K value based on K-means elbow method[J]. Computer engineering & soft-ware, 2019, 40(5): 167-170.
[39] 罗赟骞, 夏靖波, 陈天平. 网络性能评估中客观权重确定方法比较[J]. 计算机应用, 2009, 29(10): 2624-2626, 2631.
LUO Y Q, XIA J B, CHEN T P.Comparison of objective weight determination methods in network performance evaluation[J]. Journal of computer applications, 2009, 29(10): 2624-2626, 2631.
[40] 武建新, 张志鸿. 融合用户评分与显隐兴趣相似度的协同过滤推荐算法[J]. 计算机科学, 2021, 48(5): 147-154.
WU J X, ZHANG Z H.Collaborative filtering recommendation algorithm based on user rating and similarity of explicit and implicit interest[J]. Computer science, 2021, 48(5): 147-154.
[41] HA S H, PARK S C.Application of data mining tools to hotel data mart on the Intranet for database marketing[J]. Expert systems with applications, 1998, 15(1): 1-31.