Summary

A mobile and machine learning system that classifies disaster- related text and extracts key information such as disaster type, location, impact, and time using NLP techniques. This was a group college project, developed as part of research work at Badan Nasional Penanggulangan Bencana (BNPB) The system was designed to automate disaster information extraction using Natural Language Processing (NLP), improving structured understanding of unstructured text data. It provides classification and entity extraction using Named Entity Recognition (NER) and Indonesian NER (INER), supported by a custom-built NLP model.

Impact

I developed a REST API using Flask to serve the machine learning model and enable communication between the mobile application and backend system. I also contributed to building an interactive Streamlit dashboard to visualize the NLP pipeline and model processing flow. The system delivered an end-to-end workflow combining mobile app, NLP model, backend API, and visualization dashboard, demonstrating how AI can be applied to real-world disaster information processing.

What I Learned

Through this project, I gained experience in NLP model development, backend API design, system integration, and building explainable AI workflows using visualization tools.

Screenshots