基于带权三元闭包的知识图谱的构建方法研究
|
摘要
[目的/意义]随着时代的发展,基于关键字匹配的传统搜索方式已经不能满足人们的需求,而知识图谱正是为了满足人们在海量数据中搜索信息而产生的,目前构建社交平台的知识图谱是一个人们极为需求但研究较少的领域。[方法/过程]爬取新浪微博四个官博取其自2017年8月1日至2018年8月1日所发微博的正文及其他相关数据,并以其39 023条数据为样本。在利用共现方式标注共现次数的基础上,实现新的基于带权三元闭包来构建时政类微博的知识图谱,并改变相关参数与人工标注相较得出其最佳参数,从而生成最佳知识图谱。[结果/结论]运用以带权三元闭包为基础构建时政类微博知识图谱的方法,在一定参数约束下,可以生成符合期望的以亲密程度为关系的知识图谱。
[Purpose/Significance]As the world develops, people's needs have changed. The traditional keyword matching search method has not satisfied people's needs. And the use of knowledge graph search has emerged, which enables people to obtain information in massive data. Currently, the knowledge graph that builds a social platform is an area that is extremely demanded but less researched.[Method/Process]The data in this article comes from Sina Weibo, including the microblog content and related data of four of the official Weibo posts from August 1, 2017 to August 1, 2018, and takes its 39 023 data as a sample. On the basis of using the co-occurrence method to mark the co-occurrence times, realizing the knowledge graph of current political Weibo based on the construction of weighted triadic closure, and the relevant parameters are compared with the manual annotation to obtain the optimal parameters. Through such a process, the best knowledge graph is finally obtained.[Results/Conclusion]With the method of constructing political microblog knowledge graph based on weighted triadic closure, and under certain parameter constraints, a knowledge graph that matches the expected degree of intimacy can be generated.
[Purpose/Significance]As the world develops, people's needs have changed. The traditional keyword matching search method has not satisfied people's needs. And the use of knowledge graph search has emerged, which enables people to obtain information in massive data. Currently, the knowledge graph that builds a social platform is an area that is extremely demanded but less researched.[Method/Process]The data in this article comes from Sina Weibo, including the microblog content and related data of four of the official Weibo posts from August 1, 2017 to August 1, 2018, and takes its 39 023 data as a sample. On the basis of using the co-occurrence method to mark the co-occurrence times, realizing the knowledge graph of current political Weibo based on the construction of weighted triadic closure, and the relevant parameters are compared with the manual annotation to obtain the optimal parameters. Through such a process, the best knowledge graph is finally obtained.[Results/Conclusion]With the method of constructing political microblog knowledge graph based on weighted triadic closure, and under certain parameter constraints, a knowledge graph that matches the expected degree of intimacy can be generated.
引文
[1] Sidorov G,Gelbukh A,Adorno H G,et al.Poster:Soft similarity and soft cosine measure:Similarity of features in vector space model[C].Taller de Tecnologías del Lenguaje,2014:1-14.
[2] 朱木易洁,鲍秉坤,徐常胜.知识图谱发展与构建的研究进展[J].南京信息工程大学学报(自然科学版),2017,9(6):575-582.
[3] Easley D,Kleinberg J.Networks,crowds,and markets:Reasoning about a highly connected world[M].Cambridge,UK:Cambridge University Press,2010:32-54.
[4] 许云峰,赵宁,郝雪君,等.基于三元闭包和会员闭包的社区发现算法研究[J].河北科技大学学报,2014,35(1):103-108.
[5] 胡昌平,陈果.层次视角下概念知识网络的三元关系形态研究[J].图书情报工作,2014,58(4):11-16.
[6] 高杨,张燕平,钱付兰,等.基于三元闭包的节点相似性链路预测算法[J].计算机科学与探索,2017,11(5):822-832.
[7] 谢刚.知识图谱精化研究综述[J].电子技术应用,2018,44(9):29-33,38.
[8] 冯新翎,何胜,熊太纯,等.“科学知识图谱”与“Google知识图谱”比较分析——基于知识管理理论视角[J].情报杂志,2017,36(1):149-153.
[9] Bollacker K,Evans C,Paritosh P,et al.Free base;a collaboratively created graph database for structuring human knowledge[C].New York:ACM ,2008:1247-1250 .
[10] Vrandecic D,Krotzsch M.Wikidata:A free collaborative knowledge base[J].Communications of the ACM,2014,57(10):78-85.
[11] Lehmann J,Isele R,Jakob M,et al.DBpedia-a large-scale,multilingual knowledge base extracted from Wikipedia[J].Semantic Web,2015,6(2):167-195.
[12] Rebele T,Suchanek F,Hoffart J,et al.YAGO:A multilingual knowledge base from Wikipedia ,Wordnet,and GeoNames[M].Berlin Heidelberg :Springer International Publishing,2016:177-185.
[13] 赵雪芹,王少春,刘雅宁,等.我国网络传播研究的知识图谱分析[J].情报探索,2018(9):123-129.
[14] 贾丙静,葛华,李德胜.“慕课”时代C语言知识图谱的构建[J].绵阳师范学院学报,2018(11):100-103.
[15] 王巍巍,王志刚,潘亮铭,等.双语影视知识图谱的构建研究[J].北京大学学报(自然科学版),2016,52(1):25-34.
[16] 鄂世嘉,林培裕,向阳.自动化构建的中文知识图谱系统[J].计算机应用,2016,36(4):992-996,1001.
[17] Derose P,Shen W,Chen F,et al.Building structured web community portals:A top-down,compositional,and incremental approach[C].VLDB 2007:Proceedings of the 33rd International Conference on Very Large Data Bases,New York:ACM,2007:399-410.
[18] Niu F,Zhang C,et al.DeepDive:Web-scale knowledge-base construction using statistical learning and inference[EB/OL].(2014-10-10).http://www.cs.stanford.edu/people/chri-smre/papers/deepdive_vlds.pdf.
[19] 杜亚军,吴越.微博知识图谱构建方法研究[J].西华大学学报(自然科学版),2015,34(1):27-35,89.
[20] 田红梅.试论图书馆从信息服务走向知识服务[J].情报理论与实践,2003(4):312-314.
[21] Aalabaf-Sabaghi M.Networks,crowds and markets:Reasoning about a highly connected world[J].Journal of the Royal Statistical Society:Series A (Statistics in Society),2012:175:1072-1073.
[22] 储节旺.国内图书情报领域知识管理研究方法的共词分析[J].情报杂志,2012,31(11):45-50.
[23] 孟永伟,王晓英,沈茜,等.基于三角形演化机制的社会网络模型研究[J].计算机工程与应用,2016,52(8):111-114.
[24] 吴震.社会网络建模分析及挖掘算法研究[D].杭州:浙江大学,2017:15-120
[25] Blondel V D,Senelart P P.Automatic extraction of synonyms in a dictionary[EB/OL].(2013-06-07).http://pierre.senellart.com/publications/blondel2002automatic.pdf.
[26] 崔玉洁,廖坤.借助八爪鱼采集器实现过刊网刊元数据的自动提取[J].编辑学报,2016,28(5):485-488.
[27] Bharath Ramesh,Cheng Xiang,Tong Heng Lee.Shape classification using invariant features and contextual information in the bag-of-words model[J].Pattern Recognition,2015,48(3):1894-906.
[28] 郎君,秦冰,刘挺,等.篇章共指消解研究综述[J].汉语语言与计算学报,2007,7(4):227-235.
[29] Hobbs J R.Resolving pronoun references[J].Journal of Lingua,1978,44:311-338
[30] 邢彪,根绒切机多吉.基于jieba分词搜索与SSM框架的电子商城购物系统[J].信息与电脑(理论版),2018(7):104-105,108.
[31] Du Z D.An Efficientalgorithm for discovering co-occurrence concepts through pathfinder paradigm[J].Journal of Donghua University,2006:153-156.
[2] 朱木易洁,鲍秉坤,徐常胜.知识图谱发展与构建的研究进展[J].南京信息工程大学学报(自然科学版),2017,9(6):575-582.
[3] Easley D,Kleinberg J.Networks,crowds,and markets:Reasoning about a highly connected world[M].Cambridge,UK:Cambridge University Press,2010:32-54.
[4] 许云峰,赵宁,郝雪君,等.基于三元闭包和会员闭包的社区发现算法研究[J].河北科技大学学报,2014,35(1):103-108.
[5] 胡昌平,陈果.层次视角下概念知识网络的三元关系形态研究[J].图书情报工作,2014,58(4):11-16.
[6] 高杨,张燕平,钱付兰,等.基于三元闭包的节点相似性链路预测算法[J].计算机科学与探索,2017,11(5):822-832.
[7] 谢刚.知识图谱精化研究综述[J].电子技术应用,2018,44(9):29-33,38.
[8] 冯新翎,何胜,熊太纯,等.“科学知识图谱”与“Google知识图谱”比较分析——基于知识管理理论视角[J].情报杂志,2017,36(1):149-153.
[9] Bollacker K,Evans C,Paritosh P,et al.Free base;a collaboratively created graph database for structuring human knowledge[C].New York:ACM ,2008:1247-1250 .
[10] Vrandecic D,Krotzsch M.Wikidata:A free collaborative knowledge base[J].Communications of the ACM,2014,57(10):78-85.
[11] Lehmann J,Isele R,Jakob M,et al.DBpedia-a large-scale,multilingual knowledge base extracted from Wikipedia[J].Semantic Web,2015,6(2):167-195.
[12] Rebele T,Suchanek F,Hoffart J,et al.YAGO:A multilingual knowledge base from Wikipedia ,Wordnet,and GeoNames[M].Berlin Heidelberg :Springer International Publishing,2016:177-185.
[13] 赵雪芹,王少春,刘雅宁,等.我国网络传播研究的知识图谱分析[J].情报探索,2018(9):123-129.
[14] 贾丙静,葛华,李德胜.“慕课”时代C语言知识图谱的构建[J].绵阳师范学院学报,2018(11):100-103.
[15] 王巍巍,王志刚,潘亮铭,等.双语影视知识图谱的构建研究[J].北京大学学报(自然科学版),2016,52(1):25-34.
[16] 鄂世嘉,林培裕,向阳.自动化构建的中文知识图谱系统[J].计算机应用,2016,36(4):992-996,1001.
[17] Derose P,Shen W,Chen F,et al.Building structured web community portals:A top-down,compositional,and incremental approach[C].VLDB 2007:Proceedings of the 33rd International Conference on Very Large Data Bases,New York:ACM,2007:399-410.
[18] Niu F,Zhang C,et al.DeepDive:Web-scale knowledge-base construction using statistical learning and inference[EB/OL].(2014-10-10).http://www.cs.stanford.edu/people/chri-smre/papers/deepdive_vlds.pdf.
[19] 杜亚军,吴越.微博知识图谱构建方法研究[J].西华大学学报(自然科学版),2015,34(1):27-35,89.
[20] 田红梅.试论图书馆从信息服务走向知识服务[J].情报理论与实践,2003(4):312-314.
[21] Aalabaf-Sabaghi M.Networks,crowds and markets:Reasoning about a highly connected world[J].Journal of the Royal Statistical Society:Series A (Statistics in Society),2012:175:1072-1073.
[22] 储节旺.国内图书情报领域知识管理研究方法的共词分析[J].情报杂志,2012,31(11):45-50.
[23] 孟永伟,王晓英,沈茜,等.基于三角形演化机制的社会网络模型研究[J].计算机工程与应用,2016,52(8):111-114.
[24] 吴震.社会网络建模分析及挖掘算法研究[D].杭州:浙江大学,2017:15-120
[25] Blondel V D,Senelart P P.Automatic extraction of synonyms in a dictionary[EB/OL].(2013-06-07).http://pierre.senellart.com/publications/blondel2002automatic.pdf.
[26] 崔玉洁,廖坤.借助八爪鱼采集器实现过刊网刊元数据的自动提取[J].编辑学报,2016,28(5):485-488.
[27] Bharath Ramesh,Cheng Xiang,Tong Heng Lee.Shape classification using invariant features and contextual information in the bag-of-words model[J].Pattern Recognition,2015,48(3):1894-906.
[28] 郎君,秦冰,刘挺,等.篇章共指消解研究综述[J].汉语语言与计算学报,2007,7(4):227-235.
[29] Hobbs J R.Resolving pronoun references[J].Journal of Lingua,1978,44:311-338
[30] 邢彪,根绒切机多吉.基于jieba分词搜索与SSM框架的电子商城购物系统[J].信息与电脑(理论版),2018(7):104-105,108.
[31] Du Z D.An Efficientalgorithm for discovering co-occurrence concepts through pathfinder paradigm[J].Journal of Donghua University,2006:153-156.