CommunityCommands: Command Recommendations for Software Applications
Video title (x:xx min.)
We explore the use of modern recommender system technology to address the problem of learning software applications. Before describing our new command recommender system, we first define relevant design considerations. We then discuss a 3 month user study we conducted with professional users to evaluate our algorithms which generated customized recommendations for each user. Analysis shows that our item-based collaborative filtering algorithm generates 2.1 times as many good suggestions as existing techniques. In addition we present a prototype user inter-face to ambiently present command recommendations to users, which has received promising initial user feedback.
The Learning project aims to investigate advanced techniques for assisting users in learning complicated applications. We are interested in a range of investigations from the scientific study of the human learning process to prototyping novel interaction techniques for improving the general learning mechanisms that can be applied to all applications.
Amazon recommends books to its users. Netflix recommends movies. With CommunityCommands, Autodesk will recommend command functionality to its users. CommunityCommands collects usage data from thousands of Autodesk users, through the Customer Involvement Program (CIP), and then generates personalized command recommendations using newly developed algorithms. CommunityCommands will expose users to the critical commands which they should be using, but are not aware of, accelerating the learning process.