TBD
Reference Information:
Title: Rush: repeated recommendations on mobile devices
Authors: Dominikus Baur, Sebastian Boring, and Andreas Butz of University of Munich, Munich, Germany
Summary:
This paper is about using repeated recommendations in order to make item selection from large data sets easier to manage for the end user. The goal of this research is to find ways in which to simplify search from large amounts of data on devices with two-dimensional touch interfaces.
The researchers performed a preliminary study to determine the feasibility of implementing such a system. They presented users with lists of music with which they could create playlists and used different metrics in order to determine the best and most efficient combinations. The researchers discovered that having the users create playlists comprised of their top five choices was often too restricting. Other similar combinations proved to return similar results.
Discussion:
As I thought about the implications of their study, I found that I felt it could yield some interesting benefits. I liked that they applied their study to music as their data set. I have a massive music collection I have been accumulating for almost a decade and a half. This collection is not the best ordered and sometimes I find duplicate entries.
If I had a series of tools that could make navigating the data easier, I would be greatly pleased. I know most of what I have in my collection, despite the vast size. However, I think it would be neat for their algorithm to be applied to making recommendations as such based on style, etc.
No comments:
Post a Comment