The present disclosure provides a method and device for classification model training, which belongs to the field of information technology. The method for classification model training includes: acquiring (101) sample feature vectors of a plurality of users according to at least one feature set for each of the users; determining (102) gender identifiers of the users to which the sample feature vectors belong; and conducting (103) training based on the sample feature vectors and the gender identifiers corresponding to the sample characteristic vectors to obtain a gender classification model. The gender classification model can be applied to gender classification so as to determine gender of a user according to the user's sample message, and thereby information of the sample message can be increased in amount and flexibility can be provided.
