Conceptual Modeling of Explainable Recommender Systems: An Ontological Formalization to Guide Their Design and Development

Abstract

With the increasing importance of e-commerce and the immense variety of products, users need help to decide which ones are the most interesting to them. This is one of the main goals of recommender systems. However, users’ trust may be compromised if they do not understand how or why the recommendation was achieved. Here, explanations are essential to improve user confidence in recommender systems and to make the recommendation useful.
 Providing explanation capabilities into recommender systems is not an easy task as their success depends on several aspects such as the explanation’s goal, the user’s expectation, the knowledge available, or the presentation method. Therefore, this work proposes a conceptual model to alleviate this problem by defining the requirements of explanations for recommender systems. Our goal is to provide a model that guides the development of effective explanations for recommender systems as they are correctly designed and suited to the user’s needs. Although earlier explanation taxonomies sustain this work, our model includes new concepts not considered in previous works. Moreover, we make a novel contribution regarding the formalization of this model as an ontology that can be integrated into the development of proper explanations for recommender systems.

A survey on effects of adding explanations to recommender systems

“…Given that all of these impacts that explanations might have on users can support them in meeting their needs, it's important to identify which type of user the explanations are targeted at. As a result, in work, 14 we identified the following user classification: (i) target user—the users who receive the system's recommendations, (ii) stakeholders—people who have an interest in the recommender system's success, such as product owners, investors, or entrepreneurs; (iii) developers—these users need to understand how the recommender system works in order to perform various tasks, such as debugging, maintenance, or extension; and (iv) regulatory body—users who represent legislative and government organizations that need to understand how recommender systems work in order to regulate their transparency and proper use.…”

“…Caro‐Martinez et al 14 developed a model for developing effective explanations for recommender systems. Their approach provided four important factors to consider when developing explanations for recommendation systems: the user's motivation and goals, the knowledge necessary for its development, the recommendation process itself, and the user's presentation.…”

Suspiciousness and Fast and Slow Thinking Impact on Trust in Recommender Systems

“…The following three techniques are the most often employed in recommender systems: social-aware recommender systems (Asabere, et al, 2017;Ojagh, Malek & Saeedi, 2020;Xiao, et al, 2017) that take advantage of users' social connections, robust recommender systems (Burke, O'Mahony & Hurley, 2015;Tang, et al, 2019) that filter false information such as spam and fake news, and explainable recommender systems (Zhang & Chen, 2020;Caro-Martínez, Jiménez-Díaz & Recio-García, 2021;Tsai & Brusilovsky, 2021) that offer justifications for recommended products.…”