关键词: 网络舆情, 爬虫, python, 数据挖掘与分析, 数据收集

Abstract:

With the development of the Internet, the self-media platform which based on the representation of Weibo, such as Sina Weibo, has become the fourth media which is after newspaper, broadcast and television. And it also become the main means of the internet consensus. In the early stage of the internet consensus, artificial operation is the main means to monitor. But by the rapidly development of increasing network data, the artificial operation cannot afford the requirement of the development, and it needs to operate huge of the internet consensus through automatically software. This paper introduces the research status of the network public opinion monitoring system internal and abroad, and also analyzes the core technical requirement of the network opinion monitoring system, and the method and principle of mainstream technology system. According to the characteristics of methods so far, this paper has come out the improvement measures. By using Python programming language, it also verifies the feasibility of the technical improvement measures. Meanwhile, the proposed measures which is to improve the technique, come out a certain extent enlightenment of perfecting the network public opinion monitoring system.

Key words: internet public opinion, spider, python, information mining and analysis, information gathering