The quality of OpenStreetMap (OSM) has been widely concerned as a valuable source for monitoring some sustainable development goals (SDG) indicators. Improving its semantic quality is still challenging. As a kind of solution, road type prediction plays an important role. However, most existing algorithms show low accuracy, owing to data sparseness and inaccurate description. To address these problems, we propose a novel OSM road type prediction approach via integrating multiple spatial contexts with DeepFM, named MSC-DeepFM. A deep learning model DeepFM is used for dealing with data sparseness. Moreover, multiple spatial contexts (MSC), including the features of intersecting roads, surrounding buildings, and points of interest (POIs), are distilled to describe multiple types of road more accurately. The MSC combined with geometric features and restricted features are put into DeepFM, in which the low-order and high-order features fully interact. And a multivariate classifier OneVsRest is adopted to predict road types. Experiments on OSM show that the proposed model MSC-DeepFM achieves excellent performance and outperforms some state-of-the-art methods.