PUBLIC SENTIMENT WARNING METHOD AND APPARATUS BASED ON RECURRENT NEURAL NETWORK ALGORITHM, TERMINAL AND MEDIUM

摘要

A public sentiment warning method and apparatus based on a recurrent neural network algorithm, a terminal and a medium. The method comprises: obtaining public sentiment news within a preset period of time, and determining the tendency of keywords in the public sentiment news; determining feature vectors corresponding to the keywords according to the tendency of the keywords; determining a feature sequence of the public sentiment news according to the feature vectors corresponding to the keywords; finally inputting the feature sequence of the public sentiment news into a trained recurrent neural network model to determine a public sentiment warning index; and issuing a public sentiment warning according to the public sentiment warning index. The public sentiment trend can be accurately determined, and the technical problem in the prior art of a poor public sentiment development trend prediction effect is solved.