Explaining to users why some items are recommended is critical, as it can help users to make better decisions, increase their satisfaction, and gain their trust in recommender systems (RS). However, existing explainable RS usually consider explanation as a side output of the recommendation model, which has two problems: (1) it is difficult to evaluate the produced explanations because they are usually model-dependent, and (2) as a result, how the explanations impact the recommendation performance is less investigated. In this paper, explaining recommendations is formulated as a ranking task, and learned from data, similar to item ranking for recommendation. This makes it possible for standard evaluation of explanations via ranking metrics (e.g., NDCG). Furthermore, we extend traditional item ranking to an item-explanation joint-ranking formalization to study if purposely selecting explanations could achieve certain learning goals, e.g., improving recommendation performance. A great challenge, however, is that the sparsity issue in the user-item-explanation data would be inevitably severer than that in traditional user-item interaction data, since not every user-item pair can be associated with all explanations. To mitigate this issue, we propose to perform two sets of matrix factorization by considering the ternary relationship as two groups of binary relationships. Experiments on three large datasets verify our solution's effectiveness on both item recommendation and explanation ranking. To facilitate the development of explainable RS, we plan to make our code publicly available.
翻译:向用户解释为什么建议某些项目至关重要,因为这可以帮助用户作出更好的决定,提高满意度,并赢得他们对建议系统的信任。然而,现有的可解释的RS通常将解释作为建议模式的附带产出,这有两个问题:(1) 很难评价提出的解释,因为它们通常依赖模型,(2) 结果,解释如何影响建议的业绩。在本文件中,解释建议是一项分级任务,从数据中学习,类似于建议的项目分级。这样,就可以通过排名衡量标准(例如NDCG)对解释进行标准评价。此外,我们把传统项目分级扩大到项目分级联合正规化,研究有意选择解释能否达到某些学习目标,例如改进建议性能。然而,一个巨大的挑战是,用户-项目分级数据中的宽松问题将不可避免地比传统的用户-项目互动数据更严重,因为并非所有用户-项目配对都能够与所有解释相联系。为了减轻这一差异,我们提议通过两种公开的排序,我们通过实验性关系来核查两个关系,例如:改进建议业绩。