Research on Hot Words Mining Algorithm of University Network Public Sentiment

摘要

Hot words are the topic of concern of the netizens, which can help the management department to monitor the public opinion of the network. Due to the large degree of freedom, irregular syntax and immediacy of data, it is difficult for data engine to grasp text hotspots accurately through traditional text analysis. This paper deals with the text features of a time span, and determines whether it is a hot word by adding the time information of the span. Through experiments, the hot words excavated correspond to the corresponding hot events. This shows that the method proposed in this paper has a good effect and can be further studied.