Smart cities are one of the emerging domains for computational applications. Many of these applications may benefit from the ubiquitous computing paradigm to provide better services. An important aspect of these applications is how to obtain data about their users and understand them. Context-aware approaches has been proven to be successful in understanding these data. These solutions obtain data from one or more sensors and apply context recognition techniques to infer higher level information. Several works in the last decade have presented ubiquitous approaches for context recognition that can be applied in smart cities. Our work presents a systematic mapping that provides an overview of context recognition approaches applied in smart cities domains. Several aspects of these approaches have been analyzed, such as reasoning techniques, sensors usage, context level, and applications. Of the total 3627 papers returned in the search, 93 papers were analyzed after two filtering processes. The analysis of these papers have shown that only few recent works explored situation recognition information and the full potential of the sensing capabilities in smart cities.The main objective of this article is the identification of future open context recognition approaches allowing the development of news solutions and research.