Search

Despite the acknowledgment that the perception of explanations may vary considerably between end-users, explainable recommender systems (RS) have traditionally followed a one-size-fits-all model, whereby the same explanation level of detail is provided to each user, without taking into consideration individual user's context, i.e., goals and personal characteristics. To fill this research gap, we aim in this paper at a shift from a one-size-fits-all to a personalized approach to explainable recommendation by giving users agency in deciding which explanation they would like to see. We developed a transparent Recommendation and Interest Modeling Application (RIMA) that provides on-demand personalized explanations of the recommendations, with three levels of detail (basic, intermediate, advanced) to meet the demands of different types of end-users. We conducted a within-subject study (N=31) to investigate the relationship between user's personal characteristics and the explanation level of detail, and the effects of these two variables on the perception of the explainable RS with regard to different explanation goals. Our results show that the perception of explainable RS with different levels of detail is affected to different degrees by the explanation goal and user type. Consequently, we suggested some theoretical and design guidelines to support the systematic design of explanatory interfaces in RS tailored to the user's context., Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization (UMAP'22)

Enhancing explainability in recommender systems has drawn more and more attention in recent years. In this paper, we address two aspects that are under-investigated in explainable recommendation research, namely providing explanations that focus on the input (i.e. user model) and presenting personalized explanations with varying level of details. To address this gap, we propose the transparent Recommendation and Interest Modeling Application (RIMA) that aims at opening, scrutinizing, and explaining the user's interest model based on three levels of details. The results of a preliminary interview-based user study demonstrated potential benefits in terms of transparency, scrutability, and user satisfaction with the explainable recommender system. OA platinum

In this paper, we shed light on two important design choices in explainable recommender systems (RS) namely, explanation focus and explanation level of detail. We developed a transparent Recommendation and Interest Modeling Application (RIMA) that provides on-demand personalized explanations of the input (user model) and output (recommendations), with three levels of detail (basic, intermediate, advanced) to meet the demands of different types of end-users. We conducted a within-subject study to investigate the relationship between explanation focus and the explanation level of detail, and the effects of these two variables on the perception of the explainable RS with regard to different explanation aims. Our results show that the perception of explainable RS with different levels of detail is affected to different degrees by the explanation focus. Consequently, we provided some suggestions to support the effective design of explanations in RS.

The aim of learning analytics is to turn educational data into insights, decisions, and actions to improve learning and teaching. Many of the learning analytics applications behave often as a black-box. The reasoning of the provided insights, decisions, and actions are often not explained to the end-user, and this can lead to trust issues when interventions, feedback, and recommendations fail. This proposal describes the goal and activities of the LAK 2020 full-day workshop on the design and development of explainable learning analytics applications that provide transparent insights and explain decisions and actions to the intended end-users with visualisations. The main theme of the workshop is to explore how user interfaces that explain how decisions and actions were taken can strengthen the adoption of learning analytics applications. The key findings, recommendations, and conclusions of the workshop will be presented in a summarising report, highlighting best practices as well as future work opportunities. ispartof: pages:477-479 ispartof: Companion Proceedings of the 10th International Conference on Learning Analytics & Knowledge LAK20 pages:477-479 ispartof: 10th International Conference on Learning Analytics & Knowledge LAK20 location:Frankfurt, Germany date:23 Mar - 27 Mar 2020 status: published

Dissertation, RWTH Aachen University, 2018; Aachen 1 Online-Ressource (xviii, 183 Seiten) : Illustrationen, Diagramme (2018). = Dissertation, RWTH Aachen University, 2018, During the last few years, Learning Analytics (LA) has gained the interest of researchers in the field of Technology Enhanced Learning (TEL). Generally, LA deals with the development of methods that harness educational data sets to support the learning process. It shares a movement from data to analysis to action to learning. Recently, the demand for self-organized, networked, and lifelong learning opportunities has increased. Therefore, there is a need to provide an understanding of how different learners learn in these open learning settings and how learners, educators, institutions, and researchers can best support this process. Moreover, this openness should be reflected in the conceptualization and development of innovative LA approaches in order to achieve more effective learning experiences. Open Learning Analytics (OLA) is an emerging research field that has the potential to deal with these challenges in open learning environments. However, the concrete solutions and implementations that can deliver an effective and efficient OLA are still lacking. Most solutions currently available does not continuously involve end-users in the LA process and follow design patterns which make it difficult to adopt new user requirements. Furthermore, the available implementations are designed and developed for specific scenarios, which address the requirements of a specific set of stakeholders by relying on a predefined set of questions and indicators. These limitations restrict the scope of such solutions and implementations in the context of OLA targeting various stakeholders with different needs. The aim of this dissertation is to introduce personalization in the LA process by investigating the design of an effective user-centered Open Learning Analytics Platform (OpenLAP) and providing its conceptual, implementation, and evaluation details. OpenLAP provides a user-friendly interface that supports an interactive, exploratory, and real-time user experience to allow the end-users to dynamically define new indicators that meet their goals. Moreover, OpenLAP is designed to be modular and extensible allowing easy integration of new data sources, analytics methods, and visualization techniques at runtime to adopt the new requirements of multiple stakeholders and deliver an ecosystem for OLA. The main contributions of this dissertation include (1) a comprehensive analysis of the currently available LA tools and solutions with respect to their support for openness and personalization, (2) a theoretically sound design of a user-centered OpenLAP based on the requirements gathered from the empirical analysis of the literature, (3) a concrete implementation of OpenLAP providing an interface to self-define the indicators and an extensible mechanism to easily integrated new data sources, analytics methods, and visualization techniques, and (4) a thorough evaluation of OpenLAP in a pilot study at RWTH Aachen University to assess it in terms of usability, usefulness, extensibility, and modularity., Published by Aachen