论文部分内容阅读
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.
Corruption seriously affects social development and people’s confidence. This article obtains Internet Document Corpus from three different sources: anti-corruption circular of the Central Discipline Inspection Commission, new posts of “End of World Talking” and “Baidu Hot News News” Anti-corruption achievements since the LDA topic model to detect anti-corruption topics in different corpora, and the temporal and spatial characteristics of the corpus to analyze the official resume through the establishment of “officials of the official network” to explore corrupt officials and gang together with the time, level and field information Analyzing the anti-corruption tactics of high-level officials.The results show that the different corpora related to corrupt officials have different spatiotemporal distributions and different topics of corruption-related topics, and that “official network” is of great significance to the study of the complex relations among corrupt officials.