Explainable Recommendation with Comparative Constraints on Product Aspects

Trung-Hoang Le, Hady W. Lauw

Abstract: To aid users in choice-making, explainable recommendation models seek to provide not only accurate recommendations but also accompanying explanations that help to make sense of those recommendations. Most of the previous approaches rely on evaluative explanations, assessing the quality of an individual item along some aspects of interest to the user. In this work, we are interested in comparative explanations, the less studied problem of assessing a recommended item in comparison to another reference item. In particular, we propose to anchor reference items on the previously adopted items in a user's history. Not only do we aim at providing comparative explanations involving such items, but we also formulate comparative constraints involving aspect-level comparisons between the target item and the reference items. The framework allows us to incorporate these constraints and integrate them with recommendation objectives involving both types of subjective and objective aspect-level quality assumptions. Experiments on public datasets of several product categories showcase the efficacies of our methodology as compared to baselines at attaining better recommendation accuracies and intuitive explanations.