Editorial: User Modeling and Recommendations

Denis Helic, Ujwal Gadiraju, Marko Tkalcic

Abstract: The behavior of users in the digital world (e.g. online shopping, social media activity, etc.) is increasingly supported by recommender systems [Ricci et al., 2015]. Recommender systems are mainly data-driven, based on behavioral data, such as ratings, likes, purchases or general interaction and consumption [Bell et al., 2007]. Although these systems are useful for both users and service providers, they have several drawbacks including the cold start problem (i.e., the data sparsity in the initial stages of system deployment), various biases resulting from biases in the user-generated data [Ntoutsi et al., 2020] (i.e., gender, popularity, or selection bias) or the limited explainability of the data (i.e., using data without understanding the root cause of behaviors). Hence, recent work has started to adopt approaches that include sophisticated user analysis and modeling as well as algorithms that reduce biases [Elahi et al., 2021] and generate fair and explainable recommendations [Zhang and Chen, 2020].Frequently, these intelligent systems take advantage of psychological models to explain and predict user interactions with the systems [Tkalcic and Chen, 2015], influence user interaction through novel interfaces [Gupta et al., 2022], and allow for a deeper understanding of user behavior [Wölbitsch et al., 2019], including user trust in the systems [Erlei et al., 2020], and their reliance on such systems [Tolmeijer et al., 2021, Erlei et al., 2022, user preferences and needs...