Domain-Specific Semantic Relatedness From Wikipedia: Can A Course Be Transferred?

Semantic relatedness, or its inverse, semantic distance, measures the degree of closeness between two pieces of text determined by their meaning. Related work typically measures semantics based on a sparse knowledge base such as WordNet1 or CYC that requires intensive manual efforts to build and maintain. Other work is based on the Brown corpus, or more recently, Wikipedia. Wikipediabased measures, however, typically do not take into account the rapid growth of that resource, which exponentially increases the time to prepare and query the knowledge base. Furthermore, the generalized knowledge domain may be difficult to adapt to a specific domain. To address these problems, this paper proposes a domain-specific semantic relatedness measure based on part of Wikipedia that analyzes course descriptions to suggest whether a course can be transferred from one institution to another. We show that our results perform well when compared to previous work.