Abstract：The corruption greatly affects the development of the society as well as individual's confidence in the society. We analyze the fruits of anti-corruption from different perspectives based on three kinds of corpora:announcement on the website of Central Commission for Discipline Inspection, Tianya posts and Hot Search Words related News (HSWS). LDA topic model is used to detect anti-corruption related topics and the network of corruption officials is built. It is found that the temporal and spatial distributions of the different corpora related to corrupt officials are different. Anti-corruption related topics in the corpora have different emphasis. The corrupt officials' network where they co-work is of great significance for the study of their relationship.
苑鹏佳, 唐锡晋. 基于跨媒体数据的反腐多视角分析[J]. 系统工程理论与实践, 2017, 37(7): 1833-1841.
YUAN Pengjia, TANG Xijin. Multi view analysis of anti-corruption based on cross-media data. Systems Engineering - Theory & Practice, 2017, 37(7): 1833-1841.
[1] Gyimah B K. Corruption, economic growth, and income inequality in Africa[J]. Economics of Governance, 2002, 3(3):183-209. [2] 南旭光. 官僚作风和行政腐败对创业及融资的影响[J]. 系统工程理论与实践, 2009, 29(11):93-99.Nan X G. Effects of bureaucratism and administrative corruption on entrepreneurship and start-up financing[J]. Systems Engineering——Theory & Practice, 2009, 29(11):93-99. [3] Vargas G A, Schlutz D. Opening public officials' coffers:A quantitative analysis of the impact of financial disclosure regulation on national corruption levels[J]. European Journal on Criminal Policy and Research, 2016, 22(3):439-475. [4] Oyadiran P. Corruption:Threat to democracy and market economy in Nigeria[J]. Journal of Research in National Development, 2015, 13(1):1-9. [5] Grieve M, Kasim F, Kathirgamu K, et al. Anti-Corruption Programming Initiatives Report:Research on the complex and evolving fi eld of anti-corruption programming[R]. Hubert H. Humphrey School of Public Affairs, University of Minnesota, USA. Retrieved from the University of Minnesota Digital Conservancy, http://hdl.handle.net/11299/181434. [6] 付举磊, 肖进, 孙多勇, 等. 基于社会网络的恐怖活动时空特征分析[J]. 系统工程理论与实践, 2015, 35(9):2324-2332.Fu J L, Xiao J, Sun D Y, et al. Spatial-temporal characteristics analysis of terrorist activities based on social network analysis[J]. Systems Engineering——Theory & Practice, 2015, 35(9):2324-2332. [7] Saatviga S, Giuseppe V, Nello C. Automated analysis of the US presidential elections using Big Data and network analysis[J]. Big Data & Society, 2015:1-28. [8] Eytan B, Solomon M, Adamic A. Exposure to ideologically diverse news and opinion on Facebook[J]. Science, 2015, 348(6239):1130-1132. [9] Wang H, Can D, Kazemzadeh A, et al. A system for real-time twitter sentiment analysis of 2012 us presidential election cycle[C]//Proceedings of the ACL 2012 System Demonstrations. Association for Computational Linguistics, 2012:115-120. [10] King G, Pan J, Roberts M E. Reverse-engineering censorship in China:Randomized experimentation and participant observation[J]. Science, 2014, 345(6199):1251722. [11] Cao L, Tang X J. Topics and trends of the on-line public concerns based on Tianya forum[J]. Journal of Systems Science and Systems Engineering, 2014, 23(2):212-230. [12] 张泽代, 唐锡晋. 面向天涯论坛的Web挖掘的初步研究[C]//系统科学与管理科学新理论, 新方法, 新技术及应用. 第十一届全国青年系统科学与管理科学学术会议暨第七届物流系统工程学术研讨会论文集. 武汉理工大学出版社, 2011:199-204.Zhang Z D, Tang X J. A preliminary study of web mining for Tianya forum[C]//Proceedings of the 11th Youth Conference on Systems Science and Management Science, Wuhan:Wuhan University of Science and Engineering Press, 2011:199-204. [13] Hu Y, Tang X. Using support vector machine for classification of Baidu hot word[C]//International Conference on Knowledge Science, Engineering and Management. Springer Berlin Heidelberg, 2013:580-590. [14] Blei D M, Ng A Y, Jordan M I. Latent dirichlet allocation[J]. Journal of Machine Learning Research, 2003, 3(Jan):993-1022. [15] Newman M E. Coauthorship networks and patterns of scientific collaboration[J]. Proceedings of the National Academy of Sciences, 2004, 101:5200-5205.
2017, Vol. 37 
