Data Mining for Thesaurus Generation in Informal Design Information Retrieval
Maria C. Yang, William H. Wood, Mark R. Cutkosky · 1998
Design is the evolutionary process of transforming informal requirements into a product. Whether this product is real or virtual, mass produced or made to order, the information development that produces this transformation is generic. The task we focus on here is that of making textual information more useful throughout the design process. Design information can cover a range of different activities within the design process, from conceptual design to implementation. We focus on information captured in electronic notebooks. The informal information found in these notebooks is of particular interest because it is captured as it is generated, in effect, capturing the design process. In this paper, we examine techniques for improving access to such informal design information using hierarchical thesauri overlaid on generic information retrieval tools. We examine several approaches to creating thesauri, using both manual and data mining techniques, and compare the tradeoffs of each strategy. Our main goal is to develop methods for search and retrieval that allow designers and engineers access to past information and encourage design information reuse.