Recommender systems are ubiquitous in most of our interactions in the current digital world. Whether shopping for clothes, scrolling YouTube for exciting videos, or searching for restaurants in a new city, the recommender systems at the back-end power these services. Most large-scale recommender systems are huge models trained on extensive datasets and are black-boxes to both their developers and end-users. Prior research has shown that providing recommendations along with their reason enhances trust, scrutability, and persuasiveness of the recommender systems. Recent literature in explainability has been inundated with works proposing several algorithms to this end. Most of these works provide item-style explanations, i.e., `We recommend item A because you bought item B.' We propose a novel approach, RecXplainer, to generate more fine-grained explanations based on the user's preference over the attributes of the recommended items. We perform experiments using real-world datasets and demonstrate the efficacy of RecXplainer in capturing users' preferences and using them to explain recommendations. We also propose ten new evaluation metrics and compare RecXplainer to six baseline methods.
翻译:在当今数字世界中,我们的大多数互动都是无处不在的推荐系统。无论是购物衣物、滚动YouTube拍摄令人振奋的视频,还是在新城市寻找餐馆,这些服务的后端动力都是推荐系统。大多数大型推荐系统都是在广泛的数据集方面受过培训的巨型模型,是其开发者和终端用户的黑箱。先前的研究显示,提供建议及其理由会增强推荐者系统的信任、可视性和说服性。最近的解释性文献与为此提出数种算法的作品相去甚远。这些作品大多提供了项目型解释,即“我们建议项目A是因为你买了项目B。”我们提出了一个新颖的方法,即 RecXplainer,以用户对推荐项目属性的偏好为基础,产生更精细的解释。我们使用真实的数据集进行实验,并展示 RecXplainer在获取用户偏好和使用它们来解释建议方面的效率。我们还提出了10项新的评价指标,并将 RecXplainer 与6个基线方法进行比较。