Generating Recommendations From Multiple Data Sources: A Methodological Framework for System Design and Its Application

Abstract

Recommender systems (RSs) are systems that produce individualized recommendations as output or drive the user in a personalized way to interesting or useful objects in a space of possible options. Recently, RSs emerged as an effective support for decision making. However, when people make decisions, they usually take into account different and often conflicting information such as preferences, long-term goals, context, and their current condition. This complexity is often ignored by RSs. In order to provide an effective decision-making support, a RS should be "holistic", i.e., it should rely on a complete representation of the user, encoding heterogeneous user features (such as personal interests, psychological traits, health data, social connections) that may come from multiple data sources. However, to obtain such holistic recommendations some steps are necessary: first, we need to identify the goal of the decision-making process; then, we have to exploit common-sense and domain knowledge to provide the user with the most suitable suggestions that best fit the recommendation scenario. In this article, we present a methodological framework that can drive researchers and developers during the design process of this kind of "holistic" RS. We also provide evidence of the framework validity by presenting the design process and the evaluation of a food RS based on holistic principles.

Exploring the Effects of Natural Language Justifications in Food Recommender Systems

“…The Profiler module initiates the process to obtain information on a user. It implements a profiling strategy based on the holistic user modeling paradigm [5][6][7]34], which has already been used in previous studies concerning food recommendations [35]. Table 1 outlines the seven user aspects used, which are encoded in each user profile: demographics, preferences, goals, affect, behavioral data, health data, and domain-related information.…”

“…Table 2) to promote our healthy recommendations. 7 We examined the effectiveness across all meal types, as well as per type. Table 3 describes four different logistic regression analyses, which each predicted whether our health-aware recommendation was chosen (compared to a popularity-based choice or no recipe chosen).…”

“…The model across all meal types in Table 3 shows that three justification strategies effectively supported health-aware choices. A comparison of the food features of the two recipes (e.g., Recipe A contains less fat than Recipe B) was related to a higher likelihood of choosing the healthy recommendation compared to the no justification baseline: β = .86, 7 We also examined choices for different justification strategies across all conditions (both 'Single' and 'Comparative'), as well as for 'Single' Justifications only. Although nearly all effects pointed into a similar direction, fewer differences were significant; mostly for 'Single' justifications.…”

Choice Architecture for Nudges to Support Constructive Learning in Active Video Watching

“…to help users to change their energy consumption habits (Starke et al, 2020) or to increase the informed consent and privacy awareness of users (Bergram et al, 2020). A 'holistic' framework for the design of Choice Architecture for recommender systems is proposed in (Cena et al, 2020), including a broad set of user characteristics related to behaviour habits. To the best of our knowledge, there are no Choice Architecture frameworks for learning environments.…”

“…This can be provided with a carefully designed Choice Architecture. Similarly to recommender systems (Cena, et al, 2020), where the link between the user interaction with the system and user behaviour is made, we argue that intelligent learning environments need to adopt the Choice Architecture approach to link interaction features with desired behaviour related to the specific learning context.…”