Using Text Mining to Analyze Real Estate Classifieds

There has been an explosion of websites that manage classifieds in general, and real estate listings in particular. Many brokers have adapted their operation to exploit the potential of the web. Despite the importance of the real estate classifieds, there has been little work in analyzing such data. In fact, we are not aware of any work that attempted to analyze the textual data in real estate classifieds using data mining techniques. In this paper we propose a data mining process that exploits the textual data in real estate classifieds. We conduct the analysis on a large data set, which we gathered from three different property websites. We show that our process exploits the unstructured and ungrammatical textual features to significantly improve the prediction accuracy of a real estate unit price. We also illustrate how text mining combined with linear regression can be used to identify keywords that affect the price negatively or positively.