Improving access to and understanding of regulations through taxonomies

Industrial taxonomies have the potential to automate information retrieval, facilitate interoperability and, most importantly, improve decision making - decisions that must comply with existing government regulations and codes of practice. However, it is difficult to find those regulations and codes most relevant to a particular decision, even though they are now in digital form, and often available online. The focus of this work is to map regulations and codes to existing industry-specific taxonomies that would improve their access and retrieval and facilitate their integration with application programs. Keyword matching is a commonly used technique for mapping from a single taxonomy to a single regulation. In this paper, we examine techniques to address two other mapping problems: from a single taxonomy to multiple regulations and from multiple taxonomies to a single regulation. Those techniques - Cosine similarity, Jaccard coefficient, and market basket analysis - provide metrics for measuring the similarity between concepts from different taxonomies. We discuss these metrics and provide evaluations using examples from the building industry. These examples illustrate the potential regulatory benefits from the mapping between various taxonomies and regulations.