What to Learn Next: Recommending Commands in a Feature-Rich Environment

Despite an abundance of commands to make tasks easier to perform, the users of feature-rich applications, such as development environments, use only a fraction of the commands available. Earlier work has shown that command recommendation -- in which, given the command usage history of a set of users, the objective is to predict a command that is likely useful for the user to learn -- can improve the usage of a range of commands available within such applications. In this paper, we present a new algorithm, CoDis, which is built upon three hypotheses. First, we hypothesize that in feature-rich applications there exists co-occurrence patterns between commands. Second, we hypothesize that users of feature-rich applications have prevalent discovery patterns. Finally, we hypothesize that users need different recommendations based on the time elapsed between their last activity and the time of recommendation. We show on data submitted by many users of an integrated development environment (Eclipse) that CoDis outperforms existing approaches: compared to ADAGRAD, the best performing baseline, it achieves an improvement of 10.22% in recall, for a top-N recommendation task (N = 20).