Niessner, JuliaLudwig, ThomasSchneegass, StefanPfleging, BastianKern, Dagmar2021-09-032021-09-032021https://dl.gi.de/handle/20.500.12116/37264Nowadays, recommender systems are a fundamental part of several online services. However, most of these systems rely on collective user data and ratings or a preselection of parameters to derive appropriate recommendations. Within this paper, we examine recommendations without previous user data. We therefore designed and evaluated a knowledge-based recommender system by turning to recipe recommendations that offer alternatives for favorite recipes. We introduce and compare three versions of a given algorithm. Our evaluation shows that the knowledge-based approach may serve as a good start for deriving appropriate recommendations without prior user data. Moreover, we show that end-users’ assumptions about decisive criteria of a recommender system do not necessarily match the later actual decisive criteria.enRecommender SystemUser StudySimilarity MetricsRecipesKnowledge-based FilteringText/Conference Paper10.1145/3473856.3473888