［目的/意义］ 考虑用户兴趣和社交关系两方面的动态变化,提出融合用户动态兴趣与社交关系的学者推荐模型。［方法/过程］ 首先,利用不同学科的期刊文献作为分类语料,基于Labeled-LDA模型对学者所发博文进行学科领域判别。然后,依据KNN算法对博文进行学科分类,接着利用学科兴趣变化速率改进时间因子,计算得到学者动态兴趣相似度;根据学者间链接的数量关系计算学者的PageRank值,结合学者所发博文的时间价值计算得到全局信任度。在学者评论、推荐交互行为中引入时间权重计算学者交互信任度,综合全局信任度和交互信任度得到学者的动态社交信任度。最后,融合兴趣相似度与信任度进行学者推荐。［结果/结论］ 虚拟学术社区中融合用户动态兴趣与社交关系的学者推荐模型从动态兴趣和动态社交关系两个视角出发,能够有效提高学者推荐的质量。
[Purpose/Significance] Considering the dynamic changes of users’ interests and social relationships, this paper proposes a scholar recommendation model integrating users’ dynamic interests and social relationships. [Method/Process] Firstly, using the periodical literature of different disciplines as the classified corpus, the discipline domain of scholars’ blog posts was distinguished based on the labeled LDA model. Then KNN algorithm was used to classify blogs by discipline. At the same time, the change rate of subject interests was used to improve the time factor, and the dynamic interest similarity of scholars was calculated. The PageRank of scholars was calculated by using the quantitative relationship of links between scholars, and the global trust level was calculated by combining the PageRank and time value of blogs sent by scholars. Time weight was introduced into scholars’ comments and recommendation interaction behaviors to calculate scholars’ interactive trust level. The dynamic social trust level of scholars was obtained by integrating the global trust level and interactive trust level. Finally, the similarity of interest and trust were combined to recommend scholars. [Result/Conclusion] The scholar recommendation model integrating users’ dynamic interests and social relationships in the virtual academic community can effectively improve the quality of scholar recommendation from the perspectives of dynamic interests and dynamic social relationships.
[1] 中国互联网信息中心.第49次中国互联网络发展状况统计报告[EB/OL].[2022-02-20]. http://cnnic.cn/hlwfzyj/hlwxzbg/hlwtjbg/202202/P020220318335949959545.pdf.
[2] 王刚,郭雪梅.社交网络环境下基于用户行为分析的个性化推荐服务研究[J].情报理论与实践,2018,41(8):102-107.
[3] 刘征驰,田小芳,石庆书.网络虚拟社区知识分享治理机制[J].管理学报,2015,12(9):1394-1401.
[4] 邓卫华,易明,王伟军.虚拟社区中基于Tag的知识协同机制——基于豆瓣网社区的案例研究[J].管理学报,2012,9(8):1203-1210.
[5] 齐云飞,赵宇翔,朱庆华.在线问答社区中参与者知识行为研究综述[J].图书情报知识,2018(3):103-112.
[6] 席海涛,聂文博,李闺臣,等.在线健康社区用户交互的研究现状与进展[J].情报科学,2021,39(4):186-193.
[7] 孙思阳,张海涛,任亮,等.虚拟学术社区用户知识交流行为研究综述[J].情报科学,2019,37(1):171-176.
[8] HUNG S, LAI H, CHOU Y. Knowledge-sharing intention in professional virtual communities:a comparison between posters and lurkers[J]. Journal of the Association for Information Science & Technology, 2015,66(12):2494-2510.
[9] KANG H, HAN J, KWON G. An integrated success factor model of professional virtual communities:incorporation of the operators, members, and life cycle perspectives[J]. International journal of human-computer interaction,2019,35(14):1312-1330.
[10] 苏晓兰.学术虚拟社区用户交流模式研究[D].上海:华东师范大学,2015.
[11] NANDEZ G, BORREGO A. Use of social networks for academic purposes:a case study[J]. The electronic library,2013,31(6):781-791.
[12] 潘家武.基于领域本体的数字图书馆动态用户兴趣模型的构建[J].图书情报工作,2010,54(8):64-67.
[13] 陶永才,何宗真,石磊,等.基于加权动态兴趣度的微博个性化推荐[J].计算机应用,2014,34(12):3491-3496.
[14] 应璇,孙济庆.面向知识服务的用户兴趣动态知识空间模型研究[J].情报学报,2017,36(2):206-212.
[15] 王占,林岩.基于信任与用户兴趣变化的协同过滤方法研究[J].情报学报,2017,36(2):197-205.
[16] 王维,高岭,高全力.融合用户信任和用户兴趣漂移的协同过滤算法[J].微电子学与计算机,2019,36(7):103-108.
[17] FENG H, TIAN J, WANG H J, et al. Personalized recommendations based on time-weighted overlapping community detection[J]. Information & management, 2015, 52(7):789-800.
[18] LIU X J. An improved clustering-based collaborative filtering recommendation algorithm[J]. Cluster computing, 2017, 20(2):1281-1288.
[19] PARISERUM S, SANNASI G, ARPUTHARAJ K. An intelligent fuzzy rule-based e-learning recommendation system for dynamic user interests[J]. Journal of supercomputing. 2019,75(8):5145-5160.
[20] XU C, DING A, ZHAO K. A novel POI recommendation method based on trust relationship and spatial-temporal factors[J]. Electronic commerce research & applications. 2021(48),101060:1-10.
[21] 邱均平,余厚强.跨学科发文视角下我国图书情报学跨学科研究态势分析[J].情报理论与实践, 2013, 36(5):5-10.
[22] RAMAGE D, HALL D, NALLAPATI R, et al. Labeled-LDA:a supervised topic model for credit attribution in multi-labeled corpora[C]//Proceedings of the 2009 conference on empirical methods in natural language processing. Stroudsburg:Association for Computational Linguistics, 2009:248-256.
[23] 杨春艳,潘有能,赵莉.基于语义和引用加权的文献主题提取研究[J].图书情报工作, 2016,60(9):131-138.
[24] 吴小兰,章成志.基于社交媒体的高影响力跨学科用户发现研究[J].情报学报, 2017, 36(6):618-627.
[25] 王占,林岩.基于信任与用户兴趣变化的协同过滤方法研究[J].情报学报,2017,36(2):197-205.
[26] 刘凯玉.基于合作与引文网络的学者学术影响力评价研究[D].济南:山东师范大学,2019.
[27] 王玉斌.基于信息内容时效性改进推荐算法的策略研究与实现[D].北京:北京邮电大学,2013.
[28] 高慧颖,魏甜,刘嘉唯.基于用户聚类与动态交互信任关系的好友推荐方法研究[J].数据分析与知识发现, 2019, 3(10):66-77.
[29] 刘凯玉.基于合作与引文网络的学者学术影响力评价研究[D].济南:山东师范大学,2019.
[30] 董伟,陶金虎.融合PageRank与评论情感倾向的在线健康社区用户影响力研究[J].图书情报工作,2021,65(11):1-10.
[31] 曾文,桂婕,徐红姣,等.基于领域的科技文献重要度评估方法研究[J].情报理论与实践,2015,38(12):73-76.
[32] 赖院根,王星.面向检索排序的论文重要度测算[J].情报理论与实践,2009,32(10):78-81.
[33] 熊回香,孟璇,叶佳鑫.基于关键词语义类型和文献老化的学术论文推荐[J].现代情报,2021,41(1):13-23.
[34] 高慧颖,魏甜,刘嘉唯.基于用户聚类与动态交互信任关系的好友推荐方法研究[J].数据分析与知识发现,2019,3(10):66-77.
[35] 张颖怡,章成志,陈果.学术博客用户的博文分类行为研究——以科学网博客为例[J].情报学报,2016,35(11):1223-1232.
[36] 吴昊,刘东苏.社交网络中的好友推荐方法研究[J].现代图书情报技术,2015,254(1):59-65.
[37] 胡文江,胡大伟,高永兵,等.基于关联规则与标签的好友推荐算法[J].计算机工程与科学, 2013, 35(2):109-113.作者贡献说明:顾佳云:提出研究方案、数据采集与处理、论文撰写与修订;熊回香:提出研究方向和研究思路;肖兵:论文修改。
