Use of social media and Natural Language Processing (NLP) in natural hazard research

Twitter is a microblogging service for sending short, public text messages (tweets) that has recently received more attention in scientific community. In the works of Sasaki et al. (2010) and Earle et al. (2011) the authors explored the real-time interaction on Twitter for detecting natural hazards (e.g., earthquakes, typhoons) based on the user's tweets on twitter. An inherent challenge for such an application is the natural language processing (NLP), which basically consists in converting the words in numbers (vectors and tensors) in order to (mathematically/ computationally) make predictions and classifications. Recently advanced computational tools have been made available for dealing with text computationally. In this report were implemented a NLP machine learning with TensorFlow, an end-to-end open source platform for machine learning, to process and classify events based on files containing only text.