Disaster Tweets Classification using BERT-Based Language Model
This work addresses the need for automated disaster monitoring for agencies like relief organizations and news outlets, but it is incremental as it applies an existing BERT method to a specific domain.
The study tackled the problem of detecting disaster-related emergencies from social media posts by creating a BERT-based language model to classify tweets, achieving a classification accuracy of 92% on a dataset of 10,000 tweets.
Social networking services have became an important communication channel in time of emergency. The aim of this study is to create a machine learning language model that is able to investigate if a person or area was in danger or not. The ubiquitousness of smartphones enables people to announce an emergency they are observing in real-time. Because of this, more agencies are interested in programmatically monitoring Twitter (i.e. disaster relief organizations and news agencies). Design a language model that is able to understand and acknowledge when a disaster is happening based on the social network posts will become more and more necessary over time.