GO TO GITHUB

The purpose of this project is to build a Natural Lßanguage Processing (NLP) model to classify disaster messages. The web app helps categorize disaster messages into 36 categories. It also allows emergency workers to input a new message and get classification results which displays visualizations of the data.

This project is the part of Data Science Nanodegree Program by Udacity and used disaster messages provided by Figure Eight. The dataset contains labeled tweets and messages from real-life disaster events.

I built an ETL pipeline to clean, engineer features and analyze data. ML pipeline also helps automate building a machine learning model, and classify disaster messages.