基于跨媒体数据的反腐多视角分析

发布时间：2018-05-27 07:18

  本文选题：反腐 + 腐败团伙　； 参考：《系统工程理论与实践》2017年07期

【摘要】：腐败严重影响社会发展和民众信心,本文获取中纪委反腐通告、"天涯杂谈"新发帖和"百度热搜新闻词"三种不同来源的互联网文本语料从多个视角分析十八大以来的反腐成果.使用LDA话题模型探测不同语料中的反腐话题,并对语料的时空特性进行分析,通过官员履历构建"官员共职网络"探索腐败官员团伙并结合时间、级别和领域信息分析高级别官员的反腐策略.结果表明,腐败官员相关的不同语料的时空分布不同且涉及的腐败相关话题的重点不同,"官员共职网络"对于研究腐败官员的复杂关系具有重要意义.
[Abstract]:Corruption seriously affects social development and public confidence, This article obtains three kinds of Internet text data from different sources, such as the anti-corruption notice of the Central discipline Inspection Commission, the new posting of "Tianyaodan" and the "Baidu Hot search News word", and analyzes the anti-corruption achievements since the 18th National Congress of the Communist Party of China from different angles. Using the LDA topic model to explore the anti-corruption topic in different corpus, and to analyze the temporal and spatial characteristics of the corpus, through the official curriculum vitae to build "official network" to explore corrupt official groups and combine time, Level and domain information analysis of senior officials 'anti-corruption strategies. The results show that the temporal and spatial distribution of different corruption-related materials and the emphasis of corruption-related topics are different, and the "official network" is of great significance to the study of the complex relationship of corrupt officials.
【作者单位】： 中国科学院数学与系统科学研究院;
【基金】：国家重点研发计划基金项目(2016YFB1000902) 国家自然科学基金(61473284,71371107)~~
【分类号】：D262.6;TP391.1
，

本文编号：1941010