This disclosure describes systems, methods, and computer-readable media related to employing adaptive multi-feature semantic location sensing methods to estimate the semantic location of a mobile device. A set of wireless data scans associated with one or more access points at one or more locations may be received. One or more features of the one or more locations may be identified, based upon the set of wireless data scans wherein the features are associated with one or more location metrics. At least one of the one or more access points may be determined to be associated with a first location based upon, at least in part, the set of wireless data scans. A first classifier for the first location may be generated based upon, at least in part, the one or more features and the associated access points.