An essential session for anyone who is new to building taxonomies (or an inspiring refresher for those with a bit more experience). This will cover getting your project started, designing your taxonomy for business need, the reality of getting your taxonomy into production, and finally how to deal with the inevitability of organisational change.

One of the most exciting developments over the last few years has been the increasing use of taxonomies and semantic models in analysing big, complex sets of data. Hear from two specialists who are doing just that in different sectors. Joyce van Aalten will give an overview of using mindmapping techniques to generate both topdown and bottom-up taxonomies.

Two great case studies from the BBC and Pearson plc. The speakers have plenty of hands-on experience of the technical and organisational challenges (and opportunities!) of implementing taxonomies in large and complex media businesses.

Solveig and Heidi explore how the Science Library at the University of Oslo used a thesaurus to align vocabularies used by different life science disciplines, so that there is a common understanding of concepts that cut across diverse scientific fields. Roger continues the theme of using semantic models to analyse complex data.

There are many things to consider when designing and developing taxonomies, beyond what words and phrases will be included. Structure, standards, proposed usage, term choices, mappings, models, ontologies and much more will be covered by two very experienced and always pragmatic speakers.

It can be hard enough to design a taxonomy in one language, but when you start adding multiple language translations and mappings into the equation, it can easily become overwhelming. These two in-depth case studies from the UK Data Service and the Swiss National Accident Insurance Fund will provide insights and tips. Just as importantly, they will help attendees promote the benefits of doing this work within their own organisations.

Semantic technologies have come of age after many years. This session showcases how automatic classification can help in both the analysis and generation of textual content. There is also an overview of the different database technologies, such as graph and RDF, which can make semantic applications possible in your organisation.

This session is for those wanting to delve into the rapidly-maturing technologies of machine learning and NLP (natural language processing). Thomas will talk about the work of the multinational research project SSIX, which is building tools for European companies to analyse and use sentiment analysis data from social media. Michael will cover the use of machine learning in publishing, and how taxonomies can contribute to this.