[目的/意义] 挖掘图书馆借阅数据，从网络属性、节点重要性和社团模块来研究各学科书籍之间的关系，有助于指导图书资源管理、读者服务和学科建设工作。[方法/过程] 基于复杂网络的理论和方法对图书馆学生借阅数据进行分析，以各类目书籍为节点，构建图书共现网络。在此基础上，对加权网络的网络属性和节点重要性进行探讨，并通过随机游走算法划分书籍社团。[结果/结论] 研究揭示了书籍及学科间的内在联系，同时，也为加权网络的实证研究提供一定的经验材料。
[Purpose/significance] Mining library book-borrowing data and analyzing relationships among books of different subjects from the perspectives of the network attributes, the importance of nodes and community modules will contribute to guiding book resources management, library services and subject construction. [Method/process] In order to analyze the book-borrowing data of students, this paper built a co-book network whose nodes were the books of different subjects, based on the theory and methods of the complex network. On this basis, the network attributes and the importance of nodes were analyzed in a weighted network. The books were divided into different communities by Walktrap. [Result/conclusion] This research reveals the inner relationships of books, and also provides some empirical materials for empirical research of a weighted network.
[1] TIAN M. Application of chaotic time series prediction in forecasting of library borrowing flow[C] //2011 international conference on internet computing and information services. Hong Kong:IEEE, 2011:557-559.
[2] 周志峰. h指数应用于图书馆借阅数据分析的探索[J]. 图书馆建设, 2009(11):82-84,89.
[3] 龚新刚, 张娅, 沈丽娟. 图书借阅历史数据分析与预测[J]. 图书情报工作, 2015(S1):87,161-165.
[4] 付沙. 基于序列模式挖掘的图书馆用户借阅行为分析[J]. 情报理论与实践, 2014, 37(6):103-106.
[5] 段玮弘. 基于灰色-马尔柯夫模型的图书借阅行为流量预测研究[J]. 鲁东大学学报(自然科学版), 2011(3):207-212.
[6] WANG S, ZHANG C. Weighted competition scale-free network[J]. Physical review E, 2004, 70(2):066127.
[7] 燕飞, 张铭, 孙韬,等. 基于网络特征的用户图书借阅行为分析——以北京大学图书馆为例[J]. 情报学报, 2011, 30(8):875-882.
[8] 李树青, 徐侠, 许敏佳. 基于读者借阅二分网络的图书可推荐质量测度方法及个性化图书推荐服务[J]. 中国图书馆学报, 2013, 39(3):83-95.
[9] 张柯, 赵金龙, 胡小丽. 基于复杂网络理论的高校图书馆借阅网络研究[J]. 大学图书情报学刊, 2014, 32(1):75-77.
[10] VÁZQUEZ A, OLIVEIRA J G, DEZSÖ Z, et al. Modeling bursts and heavy tails in human dynamics[J]. Physical review E, 2006, 73(3):036127.
[11] 王福生, 杨洪勇. 图书管理系统中的借阅行为分析[J]. 复杂系统与复杂性科学, 2012, 9(1):55-58.
[12] 李楠楠, 张宁. 图书馆借阅网的二分图研究[J]. 复杂系统与复杂性科学, 2009, 6(2):33-39.
[13] 姚尊强, 尚可可, 许小可. 加权网络的常用统计量[J]. 上海理工大学学报, 2012, 34(1):18-26.
[14] DIJKSTRA E W. A note on two problems in connection with graphs[J]. Numerische mathematics, 1959, 1(1):269-271.
[15] OPSAHL T, AGNEESSENS F, SKVORETZ J. Node centrality in weighted networks:generalizing degree and shortest paths[J]. Social networks, 2010, 32(3):245-251.
[16] 汪小帆, 李翔, 陈关荣. 网络科学导论[M]. 北京:高等教育出版社, 2012:100, 125.
[17] BARRAT A, BARTHÉLEMY M, PASTOR-SATORRAS R, et al. The architecture of complex weighted networks[J]. Proceedings of the National Academy of Sciences of the United States of America, 2004, 101(11):3747-3752.
[18] 李拓晨, 侯磊, 李永立. 一种基于网络整体影响力的节点重要性评估方法[J]. 情报学报, 2015, 34(11):1143-1151.
[19] QI X, FULLER E, WU Q, et al. Laplacian centrality:a new centrality measure for weighted networks[J]. Information sciences, 2012, 194(5):240-253.
[20] MAITY S, RATH S K. Extended Clique percolation method to detect overlapping community structure[C] //2014 International conference on advances in computing, communications and informatics (ICACCI). New Delhi:IEEE, 2014:31-37.
[21] LU Z, SUN X, WEN Y, et al. Algorithms and applications for community detection in weighted networks[J]. IEEE transactions on parallel and distributed systems, 2015, 26(11):2916-2926.
[22] FARKAS I, ÁBEL D, PALLA G, et al. Weighted network modules[J]. New journal of physics, 2007, 9(6):180.
[23] NEWMAN M E J, GIRVAN M. Finding and evaluating community structure in networks[J]. Physical review E, 2004, 69(2):026113.
[24] PONS P, LATAPY M. Computing communities in large networks using random walks[J]. Journal of graph algorithms and applications, 2006, 10(2):191-218.
