Classification of Incoming Messages of the University Admission Campaign

Abstract

This paper deals with the task of text messages classification. The authors analyzed and reviewed the results of other researchers in this task and provided a brief overview of the machine learning and deep learning methods used in the study. The dataset of 1200 incoming messages of university admission campaign was used in the study. The authors pre-processed message texts, classified messages in three ways and applied three types of text vectorization. Based on machine learning and deep learning methods, the authors developed and applied multiclass and binary message classifiers. The paper presents classification metrics and confusion matrices for tasks of multiclass and multilabel classification. The models that provide the highest f1 score were selected as the best models.