Food Recommender Systems (FRS) have the potential to support informed and satisfying food choices. However, to realize their full potential, FRS must engage with the complexity of the choices people make around food. For example, while taste and ingredients are important, contextual and practical factors also play a critical role in food choice. Much of the previous literature on FRS has focused on ingredient-based recommendations, often in limited food datasets. Here we describe a broader approach, focusing on the use of Ensemble Topic Modelling (E_nsTM) to support personalized recipe recommendations that implicitly capture and account for multi-domain food preferences in any food-corpus. E_nsTM has the additional advantage of enabling a reduced data representation format that facilitates efficient user-modelling and recommendation. This article describes the results of two studies. The first investigated E_nsTM based recommendation in a cold-start scenario. We investigated three different E_nsTM based variations using a large-scale, real-world corpus of 230,876 recipes, and compared them with a conventional content-based approach. In a user study with 48 participants, E_nsTM-based recommenders significantly outperformed the content-based approach. Alongside excellent coverage, they enabled an implicit understanding of users’ food preference across multiple food domains. The second study investigated the use of E_nsTM in a long-term or regular-use scenario. We implemented multiple variations of feature and/or topic based hybrid recipe recommenders, which updated users’ profiles in real-time and predicted their preferences for new recipes. When compared against the current state of the art E_nsTM-based recommenders performed significantly better, providing higher accuracy and coverage.

食品推荐系统（FRS）有潜力支持知情且令人满意的食品选择。但是，为了充分发挥其潜力，FRS必须应对人们围绕食物做出的选择的复杂性。例如，尽管口味和成分很重要，但上下文和实际因素在食物选择中也起着至关重要的作用。以前有关FRS的许多文献都集中在基于成分的建议上，通常是在有限的食物数据集中。这里介绍一个更广泛的做法，注重运用合奏主题建模（Ë _ñ小号ŧ中号），以支持个性化的食谱建议，隐含捕获和账户在任何食品语料库多域食物的喜好。Ë _ñ小号ŧ中号另一个好处是可以减少数据的表示格式，从而促进有效的用户建模和推荐。本文介绍了两项研究的结果。在冷启动场景中，第一个调查了基于E _{n s} T M的推荐。我们使用了230876个食谱的真实世界大型语料库，研究了三种基于E _{n s} T M的变体，并将它们与传统的基于内容的方法进行了比较。在有48位参与者的用户研究中，E _{n s} T M基于推荐者的推荐器明显优于基于内容的推荐器。除了出色的覆盖范围之外，它们还使人们能够跨多种食品领域对用户的食品偏好产生隐含的了解。第二项研究调查了使用Ë _ñ小号ŧ中号在长期或经常使用方案。我们实现了基于功能和/或主题的混合食谱推荐器的多种变体，可实时更新用户的配置文件并预测他们对新食谱的偏好。当针对本领域的当前状态相比Ë _Ñ小号Ť中号为基础的推荐者显著更好执行，提供更高的精度和覆盖范围。