This study examines the impact of several state-of-the-art Machine Learning and Deep Learning techniques in the context of semi-supervised disaster-related twitter mining. The goal is to create a model able to successfully classify informative tweets in the context of (natural) disasters by using several approaches: - Machine Learning: Naive Bayes and Support Vector Machines - Deep Learning: Convolutional Neural Networks, Bidirectional Long Short Term Memory mechanisms. Subsequently, the supervised models are extended to assess the impact of semi-supervised techniques (self-training for NB, SVM, CNN; Virtual Adversarial Loss Function for BiLSTM).