Localized Flood DetectionWith Minimal Labeled Social Media Data Using Transfer Learning

TL;DR

This paper presents a transfer learning approach using ULMFiT to detect localized floods from social media data with minimal labeled examples, aiding emergency response and early warnings.

Contribution

It introduces a method to effectively classify flood-related social media posts in new locations using minimal labeled data and transfer learning techniques.

Findings

High accuracy with minimal labeled data

Effective localization of flood detection

Transfer learning reduces need for extensive annotations

Abstract

Social media generates an enormous amount of data on a daily basis but it is very challenging to effectively utilize the data without annotating or labeling it according to the target application. We investigate the problem of localized flood detection using the social sensing model (Twitter) in order to provide an efficient, reliable and accurate flood text classification model with minimal labeled data. This study is important since it can immensely help in providing the flood-related updates and notifications to the city officials for emergency decision making, rescue operations, and early warnings, etc. We propose to perform the text classification using the inductive transfer learning method i.e pre-trained language model ULMFiT and fine-tune it in order to effectively classify the flood-related feeds in any new location. Finally, we show that using very little new labeled data in the target domain we can successfully build an efficient and high performing model for flood detection and analysis with human-generated facts and observations from Twitter.