Weighted fusion text classification method and device

The invention relates to the field of text classification, and particularly provides a weighted fusion text classification method and device, and the method comprises the following steps: S1, training a baseline model of text classification; s2, training a plurality of non-baseline models for text classification; s3, constructing a fusion model; and S4, performing text classification by adopting the fusion model. Compared with the prior art, the method has the advantages that the text classification baseline model can be introduced, and the fusion weight is calculated according to the difference of F1 values of different text classification models and baseline models and is used for fusing scores output by different models; the problems that the fusion weight of the text classification model calculated only according to single evaluation parameters such as accuracy or recall rate is not comprehensive, and the difference of model quality during fusion cannot be reflected are solved, and the text classification