Abstract
In this paper, we discuss the potential applications and methodological challenges of using latent semantic analysis (LSA) to analyze unstructured data in real estate research. LSA is a statistical tool that allows for the analysis of large bodies of textual data by identifying specific topics or themes within the data. The purpose of this paper is to review the use of LSA as a way to understand real estate issues and to provide insight on the practical utility of the method. A typology for data complexity in the real estate context is presented. An in-depth discussion of the analytic process as a series of specific steps is provided, followed by three applications that illustrate the methodological decisions made by the analyst when LSA is performed.