A text classification method, device and computer readable storage medium

Abstract

The application provides a text classification method, device and computer readable storage medium; the method comprises the following steps: obtaining a text to be classified; performing feature extraction on the text to be classified to obtain at least one key feature to be classified and at least one context feature corresponding to each key feature to be classified; matching the at least one key feature to be classified with preset key features of each category to obtain an initial category corresponding to each key feature to be classified; for each key feature to be classified, determining a hit condition of each context feature in the at least one context feature according to a preset sample feature library of each category and the initial category; determining a classification weight of each key feature to be classified based on the hit condition of each context feature; and determining a category of the text to be classified based on the classification weight of each key feature to be classified. Through the application, the accuracy of text classification can be improved.

Images