This research proposes an approach for text classification that uses a simple neural network called Dynamic Text Classifier Neural Network (DTCNN). The neural network uses as input vectors of words with variable dimension without information loss called Dynamic Token Vectors (DTV). The proposed neural network is designed for the classification of large and short text into categories. The learning process combines competitive and Hebbian learning. Due to the combination of these learning rules the neural network is able to work in a supervised or semi-supervised mode. In addition, it provides transparency in the classification. The network used in this paper is quite simple, and that is what makes enough for its task. The results of evaluation the proposed method shows an improvement in the text classification problem using the DTCNN compared to baseline approaches.