Construction of hot spot tracking model of university network public opinion based on text clustering

From the perspective of big data, internet public opinions in higher education institutions are informative, arbitrary, invisible and abrupt. Taking consideration of these features, this paper constructs a model to tracking network public opinion hot spots in higher education institutions. Adopting data processing ways including Chinese words segmentation and text clustering based on Single-Pass, this model consists three parts: data collection, data processing and data analysis. Through this method, this paper figures out important contents among a bulk of online public opinion topics in colleges and universities and determinate hot spot topics focused by campus students.