Science is always trying to improve itself. Recently, the Natural Language Processing field (NLP) of AI is trying to come up with new methods for classifying user profiles based on what they write. This new task is called Author Profiling ([AP](https://riunet.upv.es/bitstream/handle/10251/46636/CLEF2013-AuthorProfiling.pdf?sequence=2&isAllowed=y)). Formally, AP is the task that, given a text, seeks to classify writers depending on their demographic features such as age, gender, or personality traits. There is still limited literature on the topic, and those models which address this task rely on handcrafted resources; therefore, they are restricted by the domain of the problem and by the availability of resources. In this poster, we show how to classify the personality of an author – described as a combination of five traits: openness (O), conscientiousness (C), extroversion (E), agreeableness (A), also, stability (S) – based on what they wrote on Twitter. We proposed to solve this problem using a Convolutional Neural Network (CNN) architecture developed in Python. We present how to properly train this model using a pre-trained [word embeddings](http://nlp.stanford.edu/projects/glove/) that is capable of learning the best features for the task at hand without any external dependence. The results show the potential of this approximation compared against other state-of-the-art models. We will also present several toolkits available for developing your own system in Python and we will discuss the pros and contras of them (Keras, Theano & Tensorflow). Come and see how to apply this leading edge CNN for an innovative NLP task in Python!