Behavioral-based authentication is a new research approach for user authentication. A promising idea for this approach is to use location history as the behavioral features for the user classification because location history is relatively unique even when there are many people living in the same area and even when the people have occasional travel, it does not vary from day to day. For Global Positioning System (GPS) location data, most of the previous work used longitude and latitude values. In this paper, we investigate the advantage of metadata extracted from the longitude and latitude themselves without the need to require any other information other than the longitude and latitude. That is the location identification name (i.e., the address). Our idea is based on the fact that given a pair of longitude and latitude, there is a corresponding address. This is why we use the term self-enhancing in the title. We then applied text mining on the address and combined the extracted text features with the longitude and latitude for the features of the classification. The result showed that the combination approach outperforms the GPS approach using Adaptive Boosting and Gradient Boosting algorithms.