The Impact of Explanation Facilities in User Acceptance of Expert System Advice

By L. Ye, Paul E. Johnson. 1995

How researchers see this paper

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

Citations in the corpus

Improving Robot Controller Transparency Through Autonomous Policy Explanation (2017, background): “Explanation-based approaches that justify their decisions have proven capable of increasing user acceptance of and confidence in autonomous systems [48].”
'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions (2018, background): “In some cases, explanation increases trust and reliance [33, 85, 1, 30, 60], but in others an explanation may have the opposite effect if the level of detail it contains is deemed insufficient [7].”
Explaining Recommendations: Design and Evaluation (2015, background): “When they did occur evaluations of explanations have largely focused on user acceptance of the system such as [14] or acceptance of the systems’ conclusions [87].”
Explainable Artificial Intelligence: a Systematic Review (2020, methodology): “The first methods for explainability that were tested by human users are those generating textual explanations for Expert Systems (ES) in the 90’s [334, 335].”
Evaluating XAI: A comparison of rule-based and example-based explanations (2021, unknown): “Several XAI methods try to identify examples to generate such explanations, for example those from [43–47].”
A Review of Explanation and Explanation in Case-Based Reasoning (2003, background): “Research has shown that the use of explanations make KBS predictions more acceptable to the user [Ye and Johnson, 1995; Mao and Benbasat, 2000; Ramberg, 1996).”
A systematic review and taxonomy of explanations in decision support and recommender systems (2017, background): “for future works. We also discuss limitations of our review. 5.1 Explanation Taxonomy A number of explanation taxonomies of dierent granularity levels has been proposed in the literature in the past [246,42,79,126,127,160,178,231,23,65, 130]. These taxonomies cover a variety of dierent aspects of ex”
The Impact of POMDP-Generated Explanations on Trust and Performance in Human-Robot Teams (2016, background): “We thus draw inspiration from the aims of prior researchers in “explainable AI” [33, 40], but within the novel context of decision-theoretic reasoning with uncertain beliefs.”
Collaborative Filtering beyond the User-Item Matrix (2014, background): “Two main improves user satisfaction, because users could learn to adjust their behavior and expectations to the system [Ye and Johnson 1995]. addition, it also builds trust because the users can tell if they agree with the factors inﬂuencing recommendations produced by the system.”
Designs for explaining intelligent agents (2009, background): “…design (Chandrasekaran and Swartout, 1991; Carenini and Moore, 1993; Gregor and Benbasat, 1999); (b) increase trust in system behavior and results (Ye and Johnson, 1995; Herlocker et al., 2000; McGuinness and da Silva, 2004); (c) aid comprehension and learning ARTICLE IN PRESS S.R. Haynes et al.…”
Explanation and Justification in Machine Learning : A Survey Or (2017, background): “[Ye and Johnson, 1995] experimented with three types of explanations for an expert system - trace, justiﬁcation and strategy - and found that explanations in general and justiﬁcations in particular make the generated advice more acceptable to users, and that justiﬁcation (de-ﬁned as showing the…”
Explaining Data-Driven Document Classifications (2014, background): “This often is the case with a classical decision-support system, where the system is aiding a human decision maker, for example for forecasting (Gönül et al. 2006) or auditing (Ye and Johnson 1995).”
Explanation and Argumentation Capabilities:Towards the Creation of More Persuasive Agents (2002, background): “Ye and Johnson (Ye 1995; Ye and Johnson 1995) who examined the impact of alternative types of explanations on users’ acceptance of expert system-generated advice, note that justification (i.e. explanation that provides support knowledge and requires a deep understanding of the domain) seems to be…”