Disaster Tweets Classification

Twitter is a popular social media platform where users share short posts to express their feelings. Such tweets often contain useful information about critical situations such as disasters. If that information is extracted and processed efficiently, it can drive faster, better-informed responses. However, separating disaster-related tweets from the rest is challenging due to the unstructured nature of text data.

In this project, I developed a transfer learning-based approach to detect whether a tweet is about a disaster. I fine-tuned a pretrained DistilBERT model on the Kaggle “Natural Language Processing with Disaster Tweets” dataset. The model achieves more than 83% accuracy on the test set.

Try the model yourself on Hugging Face, or read the source notebook on Kaggle.