In this paper, we study the impact of design choices for recommender systems on one-choice tasks where users want to select one item out of a variety of options. Instead of focusing on only user factors or recommendation quality, we consider how an interface design that provides the user with digital short-term memory impacts both user behavior and recommendation quality. In particular, we focus on improving recommendations and user experience through the use of shortlists. A shortlist is a temporary list of candidates that the user is currently considering, e.g., a list of a few movies the user is currently considering for viewing. Users can off-load the items they want to keep in memory to the shortlist -- thereby decreasing their cognitive load. Since shortlists are designed to support the user's task, they provide more implicit feedback naturally as part of the workflow in making decisions rather than artificially soliciting explicit feedback. This feedback provides additional data for training recommendation systems which in turn improves how well the recommendation models predict a user's preferences. We perform a user study with a movie recommendation setup to compare interfaces that offer shortlist support with those that do not. From the user studies we conclude: (i) users make better decisions with a shortlist; (ii) users prefer an interface with shortlist support; and (iii) the additional implicit feedback from sessions with a shortlist improves the quality of recommendations by nearly a factor of two.

本文研究了使用shortlists作为推荐系统的接口组件，以支持用户的决策过程，从而改善隐式反馈获取，提高推荐质量，并进行了电影推荐设置下的用户研究测试和分析，结果表明，使用带有shortlists的界面能够使用户做出更好的决策和提高推荐系统的精度。

使用短列表来支持决策，并提高推荐系统的性能