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

By Ingrid Nunes, Dietmar Jannach. 2017

384 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems

Citations in the corpus

A Survey on Conversational Recommender Systems (2020, background): “The value of explanations in general recommender systems is widely recognized [50, 101, 136].”
A Review of Taxonomies of Explainable Artificial Intelligence (XAI) Methods (2022, background): “[56] focus on explainability of recommender systems, Anjomshoae et al.”
What Do We Want From Explainable Artificial Intelligence (XAI)? - A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research (2021, background): “In fact, only a minority of papers concerned with explainability approaches also evaluated the proposed methods [12, 13].”
How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems (2019, background): “Accordingly, CBR as an area has a substantial literature on explanation [11, 12, 19], as does its sister area of recommender systems [13, 42].”
A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts (2021, background): “An example here is the long, detailed, and practically oriented survey by Nunes and Jannach from 2017 [101].”
A historical perspective of explainable Artificial Intelligence (2020, background): “…1992), and have been brought back into the focus by recent successes in machine learning technology (Guidotti et al., 2018), for both autonomous (Nunes & Jannach, 2017) and human-in-the-loop systems (Holzinger, 2016; Holzinger, Plass, et al., 2019), with applications in recommender systems…”
I Think I Get Your Point, AI! The Illusion of Explanatory Depth in Explainable AI (2021, background): “Further, the explainability of explanations is often assessed through subjective user ratings [41].”
Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities (2021, background): “It is one of the most raised challenges in the literature of XAI [1, 31, 10, 32, 9, 41, 33, 26, 43, 42, 2, 34, 8, 44, 35, 36, 37, 18, 45, 38, 39, 40, 46].”
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2022, background): “Nunes and Jannach reported that only 21% of their 190 analyzed studies (1990–2017) that presented an XAI technique or tool contained “any form of evaluation, except from toy examples” [177].”