Using Convolutional Neural Networks for Emoticon Classification

The problem of automatic classification of photographs, graphics and spatial data is increasingly being addressed via advanced machine learning methods and related models like Convolutional Artificial Neural Networks (CANN). In the scope of this work, we conducted a study of application of the CANN to an example of emoticon classification. In this paper, chosen methods are described as well as solutions for data collection and processing. Methods for training and evaluation of the model are offered. The presented results show successful application of the model.