A systematic review and taxonomy of explanations in decision support and recommender systems

Abstract

With the recent advances in the field of artificial intelligence, an increasing number of decision-making tasks are delegated to software systems. A key requirement for the success and adoption of such systems is that users must trust system choices or even fully automated decisions. To achieve this, explanation facilities have been widely investigated as a means of establishing trust in these systems since the early years of expert systems. With today's increasingly sophisticated machine learning algorithms, new challenges in the context of explanations, accountability, and trust towards such systems constantly arise. In this work, we systematically review the literature on explanations in advice-giving systems. This is a family of systems that includes recommender systems, which is one of the most successful classes of advice-giving software in practice. We investigate the purposes of explanations as well as how they are generated, presented to users, and evaluated. As a result, we derive a novel comprehensive taxonomy of aspects to be considered when designing explanation facilities for current and future decision support systems. The taxonomy includes a variety of different facets, such as explanation objective, responsiveness, content and presentation. Moreover, we identified several challenges that remain unaddressed so far, for example related to fine-grained issues associated with the presentation of explanations and how explanation facilities are evaluated.

References in corpus (1)

• Do Social Explanations Work? Studying and Modeling the Effects of Social Explanations in Recommender Systems

Cited by in corpus (31)

• What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research
• From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
• A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Concepts
• Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
• Fairness in Recommender Systems: Research Landscape and Future Directions
• Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needs
• Building Human Values into Recommender Systems: An Interdisciplinary Synthesis
• Explainability in Music Recommender Systems
• Is More Always Better? The Effects of Personal Characteristics and Level of Detail on the Perception of Explanations in a Recommender System
• Explanations of Black-Box Model Predictions by Contextual Importance and Utility
• Economic Recommender Systems -- A Systematic Review
• How Can We Develop Explainable Systems? Insights from a Literature Review and an Interview Study
• Explainability for Transparent Conversational Information-Seeking
• Yes We Care! -- Certification for Machine Learning Methods through the Care Label Framework
• Measuring the Impact of Explanation Bias: A Study of Natural Language Justifications for Recommender Systems
• Modeling and Evaluating Personas with Software Explainability Requirements
• Do Users' Explainability Needs in Software Change with Mood?
• How Does Users' App Knowledge Influence the Preferred Level of Detail and Format of Software Explanations?
• Effects of interactivity and presentation on review-based explanations for recommendations
• Justification of Recommender Systems Results: A Service-based Approach
• Play MNIST For Me! User Studies on the Effects of Post-Hoc, Example-Based Explanations & Error Rates on Debugging a Deep Learning, Black-Box Classifier
• Knowledge-based XAI through CBR: There is more to explanations than models can tell
• What was Hybrid? A Systematic Review of Hybrid Collaboration and Meetings Research
• Towards an Explanation Space to Align Humans and Explainable-AI Teamwork
• "Even explanations will not help in trusting [this] fundamentally biased system": A Predictive Policing Case-Study
• Designing Explanations for Group Recommender Systems
• Tell Me the Good Stuff: User Preferences in Movie Recommendation Explanations
• Two4Two: Evaluating Interpretable Machine Learning - A Synthetic Dataset For Controlled Experiments
• Towards Better User Requirements: How to Involve Human Participants in XAI Research
• Can Offline Metrics Measure Explanation Goals? A Comparative Survey Analysis of Offline Explanation Metrics in Recommender Systems
• "A cold, technical decision-maker": Can AI provide explainability, negotiability, and humanity?