D4.6 Specification of Information Mining and Information Quality components

Authors

Deborah Markham, Mike Hewlett, Andrew Muddiman, Christian Reuter, Thomas Ludwig, Marc-André Kaufhold, Matthias Moi, Therese Friberg, Robin Marterer, Federico Sangiorgio

Abstract

This document provides a specification of the Processing and Analysis Subsystem (PAS) of EmerGent, which contains the information mining (IM) and information quality (IQ) components. In EmerGent, a huge volume of low-quality messages will be continuously gathered from a variety of social media (SM) services. It is the role of PAS to extract and condense the key information from the raw data, generating alert messages in the common alerting protocol (CAP) format to be delivered to the Routing Subsystem. The IQ subsystem assesses the quality of the mined data, adding suitable metrics to the consolidated information, providing emergency services with an indication of the reliability of the alert.

Purpose of the document

This document is intended to provide a specification of the framework encompassing IM and IQ, allowing implementation of these components to begin in a structured fashion. It draws on knowledge of IM and IQ that has been provided in previous EmerGent documentation (D4.3: Specification of Mining Methods to Develop – Version 1).