Semantic Approach to Web-Based Discovery of Unknowns to Enhance Intelligence Gathering

Semantic Approach to Web-Based Discovery of Unknowns to Enhance Intelligence Gathering

Natalia Danilova (City University London, UK) and David Stupples (City University London, UK)
Copyright: © 2017 |Pages: 18
DOI: 10.4018/978-1-5225-2058-0.ch006
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

A semantic Web-based search method is introduced that automates the correlation of topic-related content for discovery of hitherto unknown intelligence from disparate and widely diverse Web-sources. This method is in contrast to traditional search methods that are constrained to specific or narrowly defined topics. The method is based on algorithms from Natural Language Processing combined with techniques adapted from grounded theory and Dempster-Shafer theory to significantly enhance the discovery of related Web-sourced intelligence. This paper describes the development of the method by showing the integration of the mathematical models used. Real-world worked examples demonstrate the effectiveness of the method with supporting performance analysis, showing that the quality of the extracted content is significantly enhanced comparing to the traditional Web-search approaches.
Chapter Preview
Top

Background On Web-Based Search Of Unknowns

If the Web is to be used for improving decision-making, then a more effective search method is needed to collect and correlate the best information.

Government and business decisions are made with varying degrees of certainty. Donald Rumsfeld (2002) stated: “There are ‘known knowns’ – that is things we know we know; there are ‘known unknowns’ – that is some things we know we do not know; but there are also ‘unknown unknowns’ – that is things we don't know we don't know.” Effective decision-making requires trusted, focused and relevant information. We should be comfortable with both ‘known knowns’ (KKs) and ‘known unknowns’ (KUs), as these are straightforward to find. The problem being that much of the rich information required for good decisions may be in the category of ‘unknown unknowns’ (UUs). So an important question to ask is how can we find the relevant UUs to enrich the knowledge on the topic, reduce the associated uncertainty and improve decision-making (Figure 1)?

Figure 1.

Discovery of unknowns reduces uncertainty and enhances decision quality

Recent research projects aimed at discovery of UUs focus primarily on ontology-based knowledge acquisition techniques. Lehmann et al. (2007) presented a new user interface ‘DBpedia’ to explore a large ontology-based data set by finding connections between different objects, thus, discovering UUs. The core of DBpedia is in the form of an ontology that represents background knowledge comprising structured information extracted from Wikipedia. However, this solution is limited to searches within the DBpedia data set only.

Complete Chapter List

Search this Book:
Reset