This paper presents a new data-driven approach to building a UK skills taxonomy,
improving upon the original approach developed in Djumalieva and Sleeman (2018). The
new method improves on the original method as it does not rely on a predetermined list of
skills, and can instead automatically detect previously unseen skills. This ‘minimal
judgement’ approach is made possible by a classifier that automatically detects sentences
within job adverts that are likely to contain skills. These ‘skill sentences’ are then grouped
to define distinct skills, and a hierarchy is formed. The resulting taxonomy contains three
levels and 6,685 separate skills. The taxonomy could be used as a base for developing the
first UK-specific skills taxonomy, which domain experts would then refine and extend. It
could also be used to spot regional skill clusters, and for rapid assessments of skill
changes following shocks such as the COVID-19 pandemic.
