An Empirical Methodology for Detecting and Prioritizing Needs during Crisis Events

TL;DR

This paper introduces two new methods to identify and prioritize essential needs during crises using social media data, specifically Twitter, demonstrating effectiveness in COVID-19 related scenarios.

Contribution

It presents novel techniques for detecting prioritized resources and specific needs from noisy social media data, improving crisis response strategies.

Findings

Achieved 64% precision in identifying top needs from tweets.

Reached 68% F1-score in detecting who-needs-what in annotated tweets.

Validated methods on COVID-19 crisis data.

Abstract

In times of crisis, identifying the essential needs is a crucial step to providing appropriate resources and services to affected entities. Social media platforms such as Twitter contain vast amount of information about the general public's needs. However, the sparsity of the information as well as the amount of noisy content present a challenge to practitioners to effectively identify shared information on these platforms. In this study, we propose two novel methods for two distinct but related needs detection tasks: the identification of 1) a list of resources needed ranked by priority, and 2) sentences that specify who-needs-what resources. We evaluated our methods on a set of tweets about the COVID-19 crisis. For task 1 (detecting top needs), we compared our results against two given lists of resources and achieved 64% precision. For task 2 (detecting who-needs-what), we compared our results on a set of 1,000 annotated tweets and achieved a 68% F1-score.