Disaster Tweet Detection

Twitter has become an important communication channel in times of emergency. The ubiquitousness of smartphones enables people to announce an emergency they’re observing in real-time. Because of this, more agencies are interested in programatically monitoring Twitter (i.e. disaster relief organizations and news agencies). However, it’s not always clear whether a person’s words are actually announcing a disaster. The objective of this project is to build a machine learning model that predicts which Tweets are about real disasters and which ones aren’t. I had access to a dataset of 10,000 tweets that were hand classified.

I submitted my model into a Kaggle competition titled “Natural Language Processing with Disaster Tweets“ and got an accuracy score of 78% for test data. Click the button below to view the submission on Kaggle.com, or view my complete jupyter notebook below.

Jupyter Notebook

Previous
Previous

WNBA Score Prediction with Web Scraping and Machine Learning

Next
Next

MATLAB Gun Violence Visualization App