Distributed Representation Learning for the Historical Figures Based on CBDB and Ancient Books: A Digital Humanistic Perspective

Abstract

Abstract: Humanities research in open and interconnected environment is in an urgent need of massive data resources and new approaches. This study constructs a historical social network based on a large number of data collected from the CBDB knowledge base and ancient literature, and transforms historical figures into low real-value vectors by network representation learning algorithm, which has been specifically improved for historical network by incorporating the nodes influence. Based on the concept of digital humanities, this paper carries out an empirical study on humanities computing tasks, such as person relatedness calculation and relationship mining. This work is the first attempt to introduce the network representation learning technique into the historical social network analysis, which will help researchers to mine knowledge or find clues from massive humanistic data. It will have a positive influence on the expansion of the paradigm and methodology of humanistic research.

Key words: Digital humanities, Distributed representation, Network representation learning, Social network analysis

Pan Jun. Distributed Representation Learning for the Historical Figures Based on CBDB and Ancient Books: A Digital Humanistic Perspective[J]. Libraly Journal, 2020, 39(8): 94-102.

References

[ 1 ] 欧阳剑. 大数据视域下人文学科的数字人文研究[J]. 图书馆杂志, 2018, 37(10): 61-69. [ 2 ] 金家琴, 夏翠娟. 数字人文的跨界、融合与对话——第九届上海国际图书馆论坛数字学术与人文研究分会场“快闪报告”综述[J]. 图书馆杂志, 2018, 37(12): 29-38. [ 3 ] 谭凯. 中古中国门阀大族的消亡[M]. 北京: 社会科学文献出版社, 2017. [ 4 ] 严承希, 王军. 数字人文视角: 基于符号分析法的宋代政治网络可视化研究[J]. 中国图书馆学报, 2018, 44(5): 87-103. [ 5 ] 胡静. 数字人文在韩国史研究的应用探索—— 以杂科中人社会网络分析为中心[J]. 韩国研究论丛, 2018(2): 214-233. [ 6 ] 王涛. 数字人文框架下《德意志人物志》的群像描绘与类型分析[J]. 历史研究, 2018(5): 148-166. [ 7 ] Jackson C. Using social network analysis to reveal unseen relationships in medieval Scotland [J]. Digital Scholarship in the Humanities, 2017, 32(2): 336- 343. [ 8 ] Perozzi B, Al-Rfou R, Skiena S. DeepWalk: online learning of social representations [C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, 2014: 701-710. [ 9 ] Grover A, Leskovec J. Node2vec: Scalable feature learning for networks [C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco, 2016: 855-864. [10] Tang J, Qu M, Wang M, et al. Line: Large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web. Florence, 2015: 1067-1077. [11] 涂存超, 杨成, 刘知远, 等. 网络表示学习综述[J]. 中国科学: 信息科学, 2017, 47(8): 980-996. [12] 刘炜, 林海青, 夏翠娟. 数字人文研究的图书馆学方法: 书目控制与文献循证[J]. 大学图书馆学报, 2018, 36(5): 116-123. [13] 董舞艺, 梁兴堃. 中国人文学者参与数字人文动机的二元结构及行为路径[J]. 中国图书馆学报, 2019(4): 1-18. [14] 许鑫, 陈路遥, 杨佳颖. 数字人文研究领域的知识网络演化——基于题录信息和引文上下文的关键词共词分析[J]. 情报学报, 2019, 38(3): 322- 334. [15] 柯平, 宫平. 数字人文研究演化路径与热点领域分析[J]. 中国图书馆学报, 2016, 42(6): 13-30. [16] Bengio Y, Ducharme R, Vincent P, et al. A neural probabilistic language model [J]. Journal of Machine Learning Research, 2003, 3(6): 1137-1155. [17] Mikolov T, Yi H W, Zweig G. Linguistic regularities in continuous space word representations[C]// Proceedings of the Conference of the North American Chapter of the ACL, Atlanta, Georgia, USA, 2013: 746-751. [18] Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space[EB/OL]. [2019-03