Current state-of-the-art recommender systems predominantly rely on either implicit or explicit feedback from users to suggest new items. While effective in recommending novel options, these conventional systems often use uninterpretable embeddings. This lack of transparency not only limits user understanding of why certain items are suggested but also reduces the user's ability to easily scrutinize and edit their preferences. For example, if a user has a change in interests, they would need to make significant changes to their interaction history to adjust the model's recommendations. To address these limitations, we introduce a novel method that utilizes user reviews to craft personalized, natural language profiles describing users' preferences. Through these descriptive profiles, our system provides transparent recommendations in natural language. Our evaluations show that this novel approach maintains a performance level on par with established recommender systems, but with the added benefits of transparency and user control. By enabling users to scrutinize why certain items are recommended, they can more easily verify, adjust, and have greater autonomy over their recommendations.

翻译：当前最先进的推荐系统主要依赖用户的隐式或显式反馈来推荐新物品。尽管在推荐新颖选项方面效果显著，但这些传统系统通常使用不可解释的嵌入表示。这种不透明性不仅限制了用户理解特定物品被推荐的原因，还降低了用户轻松审查和编辑自身偏好的能力。例如，当用户兴趣发生变化时，他们需要大幅修改交互历史才能调整模型的推荐结果。为解决这些限制，我们提出了一种创新方法：利用用户评论文本构建描述用户偏好的个性化自然语言画像。通过描述性画像，本系统以自然语言形式提供透明的推荐结果。评估表明，该创新方法在性能上与传统推荐系统相当，同时具备透明性与用户可控性的额外优势。通过使系统能够审查特定物品被推荐的原因，用户可以更轻松地验证、调整推荐结果，并对推荐享有更高的自主权。