Mobile HCI studies are often conducted in a highly controlled environment and with a small convenient sample. The findings cannot always be generalized to the behaviour of real users in real contexts. In contrast, researchers recently started to use apps and other wide distribution channels as an apparatus for mobile HCI research. Publishing apps in mobile application stores and public APIs for mobile services enable researchers to study large samples in their ̀natural habitat'. This workshop continues the successful Research in the Large workshop series held at UbiComp 2010 and 2011. Relevant topics include the design of large-scale studies, reaching target users, dealing with new types of evaluation data, and heterogeneous usage contexts. We seek ways to systematically collect, analyse and make sense of large datasets, potentially in real-time. The goal of this workshop is to provide a forum for researchers and developers from academia and industry to exchange experiences, insights and strategies for wide distribution of user studies towards large-scale mobile HCI research.