Mondeca for thesaurus, autotagging and ontology management in a public health statistics platform

HealthStats NSW ( www.healthstats.nsw.gov.au ) is a public platform of complex health statistics that displays information on the health of the New South Wales population taken from many data sources. The HealthStats NSW major enhancement project uses Mondeca software to create a thesaurus and ontology which improve search results and are used for automatic webpage creation to assist ‘storytelling’ and navigation. Improving the efficiency of managing content and automating Web content production frees up time and effort of specialised health statisticians and epidemiologists to develop new content and add value to existing content. This paper explores the creation of the thesaurus and its use for autotagging, creation of the ontology component and its use for webpage creation, tweaking of the automated system, and future options for the project.