Designing explanation interfaces for transparency and beyond

In this work-in-progress paper, we presented a participatory process of designing explanation interfaces for a social recommender system with multiple explanatory goals. We went through four stages to identify the key components of the recommendation model, expert mental model, user mental model, and target mental model. We reported the results of an online survey of current system users (N=14) and a controlled user study with a group of target users (N=15). Based on the findings, we proposed five set of explanation interfaces for five recommendation models (N=25) and discussed the user preference of the interface prototypes.