Towards A Skills Taxonomy (original) (raw)

When evaluating job applications, recruiters and employers try to determine whether the information that is provided by a job seeker is accurate and whether it describes an individual that possesses sufficient skills. These questions are related to the hidden skills and skills resolution problems. In this paper we argue that using a skills taxonomy to identify and resolve unknown relationships between text that describe an applicant and job descriptions is the best way for addressing these problems. Unfortunately, no comprehensive , publicly available taxonomy exists. To this end, this work proposes an automated process for creating a skills taxonomy. Effective and efficient methods for bootstrapping a taxon-omy are critical to any process that names and characterizes the properties and interrelationships of entities. To this end, we present three potential methods for bootstrapping and extending our skills taxonomy. We propose a hybrid scheme that combines the beneficial features of those methods. Our hybrid approach seeds the bootstrapping process with publicly available resources and identifies new skill terms and corresponding entity relationships. In this paper, we focus specifically on using Wikipedia as our corpus and exploiting its structure to populate the taxonomy. We begin by constructing a relationship graph of possible skill terms from Wikipedia. We then use a data mining methodology to identify skill terms. Our results are promising, and we are able to achieve a 98% classification rate.

Sign up for access to the world's latest research.

checkGet notified about relevant papers

checkSave papers to use in your research

checkJoin the discussion with peers

checkTrack your impact