Master of Disaster: A Disaster-Related Event Monitoring System From News Streams

TL;DR

The paper introduces 'Master of Disaster', an open-source system that extracts, links, and visualizes disaster-related events from news streams to aid in real-time monitoring and discrimination of event instances.

Contribution

It presents a novel system integrating event extraction, knowledge graph linking, and visualization for disaster event monitoring from news streams.

Findings

Effective extraction of disaster events from news streams.

Successful linking of events to Wikidata knowledge graph.

Visual discrimination of event instances achieved.

Abstract

The need for a disaster-related event monitoring system has arisen due to the societal and economic impact caused by the increasing number of severe disaster events. An event monitoring system should be able to extract event-related information from texts, and discriminates event instances. We demonstrate our open-source event monitoring system, namely, Master of Disaster (MoD), which receives news streams, extracts event information, links extracted information to a knowledge graph (KG), in this case Wikidata, and discriminates event instances visually. The goal of event visualization is to group event mentions referring to the same real-world event instance so that event instance discrimination can be achieved by visual screening.