The monitoring of volcanoes is mainly performed by sensors installed on their structures, aiming at recording seismic activities and reporting them to observatories to be later analyzed by specialists. However, due to the high volume of data continuously collected, the use of automatic techniques is an important requirement to support real time analyses. In this sense, a basic but challenging task is the classification of seismic activities to identify signals yielded by different sources as, for instance, the movement of magmatic fluids. Although there exists several approaches proposed to perform such task, they were mainly designed to deal with raw signals. In this paper, we present a 2D approach developed considering two main steps. Firstly, spectrograms for every collected signal are calculated by using Fourier Transform. Secondly, we set a deep neural network to discriminate seismic activities by analyzing the spectrogram shapes. As a consequence, our classifier provided outstanding results with accuracy rates greater than 95%.