As availability of Internet access on mobile devices develops year after year, users have been able to make use of search services while on the go. Location information on these devices has enabled mobile users to use local search services to access various types of location-related information easily. Mobile local search is inherently different from general web search. Namely, it focuses on local businesses and points of interest instead of general web pages, and finds relevant search results by evaluating different ranking features. It also strongly depends on several contextual factors, such as time, weather, location etc. In previous studies, rankings and mobile user context have been investigated with a small set of features. We developed a mobile local search application, Gezinio, and collected a data set of local search queries with novice social features. We also built ranking models to re-rank search results. We reveal that social features can improve performance of the machine-learned ranking models with respect to a baseline that solely ranks the results based on their distance to user. Furthermore, we find out that a feature that is important for ranking results of a certain query category may not be so useful for other categories. (C) 2016 Elsevier Inc. All rights reserved.