Utilizing microblogs for assisting post-disaster relief operations via matching resource needs and availabilities

Abstract

During a disaster event, two types of information that are especially useful for coordinating relief operations are needs and availabilities of resources (e.g., food, water, medicines) in the affected region. Information posted on microblogging sites is increasingly being used for assisting post-disaster relief operations. In this context, two practical challenges are (i) to identify tweets that inform about resource needs and availabilities (termed as need-tweets and availability-tweets respectively), and (ii) to automatically match needs with appropriate availabilities. While several works have addressed the first problem, there has been little work on automatically matching needs with availabilities. The few prior works that attempted matching only considered the resources, and no attempt has been made to understand other aspects of needs/availabilities that are essential for matching in practice. In this work, we develop a methodology for understanding five important aspects of need-tweets and availability-tweets, including what resource and what quantity is needed/available, the geographical location of the need/availability, and who needs / is providing the resource. Understanding these aspects helps us to address the need-availability matching problem considering not only the resources, but also other factors such as the geographical proximity between the need and the availability. To the best of our knowledge, this study is the first attempt to develop methods for understanding the semantics of need-tweets and availability-tweets. We also develop a novel methodology for matching needtweets with availability-tweets, considering both resource similarity and geographical proximity. Experiments on two datasets corresponding to two disaster events, demonstrate that our proposed methods perform substantially better matching than those in prior works. Additionally, our proposed methodologies are reusable across different types of disaster events.

A review of social media use during disaster response and recovery phases

“…Some explored the use of social media for post-disaster emergency response through in-depth interviews and surveys [30][31][32][33] and others explored the use of social media for post-disaster temporary memorializing, journalists' use of social media, or approaches to bridging the gap between emergency managers and the public [34][35][36]. Finally, other studies -most notably the ones conducted by Wukich and Mergel [37], and Dutt et al [38] -looked at more than one disaster event.…”

“…Further, tweets can provide potential insight about the travel patterns of social media users located in the affected areas [50]. Social media can also provide emergency managers with information on resource needs and resource availability, and in turn, match those needs with the available resources [38], including rescue personnel and volunteers [52].…”

“…• Emergency managers can deal with the issues of information overload and quality of social media data with the help of tools designed for gathering and filtering social media data [31] or supervised machine learning techniques [44,47]. • Social media can provide emergency managers with information on resource needs and resource availability and in turn match those needs with the available resources [38], including rescue personnel and volunteers [52]. • It is also important for emergency managers to understand the needs of the public in terms of disaster events [53].…”

Information Retrieval from Microblogs During Disasters: In the Light of IRMiDis Task

“…In our proposed methodology for matching need and availability tweets, first, we extracted five critical aspects associated with need and availability of resource, i.e., name of the resource, location of need/availability, the quantity of resource needed or available and sources of the resource using a dependency tree-based parser [8]. Hence, by understanding these aspects of need and availability tweets, we proposed several methodologies to match need tweet and availability tweet considering resource only and using both resource and location.…”

“…We reused the tweet collection of 50,018 English tweets related to the Nepal earthquake that occurred on 25th April 2015. 7 [9] Additionally, a collection of 6, 000 news articles, that were posted during the Nepal earthquake in April 2015 was extracted using Radian6 tool 8 and included in our collection. To annotate the dataset for identification of fact-checkable tweets (Task 1) we employed pooling.…”