CommunityCommands

Justin Matejka, Wei Li, Tovi Grossman, George Fitzmaurice

2009 · 123 citations · 42 references

Concepts

TL;DR

The work addresses command recommender systems for learning software applications, highlighting key design considerations. The authors aim to develop a command recommender system that assists users in learning software applications. They built an item‑based collaborative filtering recommender, evaluated it in a 3‑month study with professionals, and implemented a prototype UI. The algorithm produced 2.1 times more useful suggestions than existing methods, and the prototype UI received encouraging user feedback.

Abstract

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 interface to ambiently present command recommendations to users, which has received promising initial user feedback.

References

42