Improving Recommender Systems Beyond the Algorithm
This work addresses the incremental improvement of recommender systems for users and developers by shifting focus from algorithms to data generation processes.
The paper tackles the problem of improving recommender systems by focusing on user interface design to enhance feedback data quality and quantity, rather than just algorithmic improvements, and demonstrates through a user study on movie selection that interface factors like information scent and access cost can effectively shape implicit feedback while maintaining user experience.
Recommender systems rely heavily on the predictive accuracy of the learning algorithm. Most work on improving accuracy has focused on the learning algorithm itself. We argue that this algorithmic focus is myopic. In particular, since learning algorithms generally improve with more and better data, we propose shaping the feedback generation process as an alternate and complementary route to improving accuracy. To this effect, we explore how changes to the user interface can impact the quality and quantity of feedback data -- and therefore the learning accuracy. Motivated by information foraging theory, we study how feedback quality and quantity are influenced by interface design choices along two axes: information scent and information access cost. We present a user study of these interface factors for the common task of picking a movie to watch, showing that these factors can effectively shape and improve the implicit feedback data that is generated while maintaining the user experience.