Explanation facilities and interactive systems

By H. Johnson, P. Johnson. 1993

Our main research aim is to improve the provision of explanation facilities in information systems generally, and to identify what is meant by “explanation”. This paper reports research which identifies both the strengths and weaknesses of current research and shows how to overcome those weaknesses. We are also concerned with both present and future uses of explanation in information systems and the role of explanation in a broad range of interactive applications.

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

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, neutral): “…al., 2012; Cahour and Forzy, 2009; Clarke and Smyth, 1993; Davies, 2011; Dunbar, 1995; Frank et al., 2016; Groce et al., 2014; Hoffman, 2013, 2017b; Johnson and Johnson, 1993; Kilgore and Voshell, 2014, 2014; Klein and Hoffman, 2008; Klein, Moon, and Hoffman, 2006a; 2006b; Lyons, 2013; McBride,…”
'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].”
How it works: a field study of non-technical users interacting with an intelligent system (2007, methodology): “Trust, explanation, and accountability Explanation has been one of the most frequently used methods for improving trust in intelligent systems [12] by making their behavior more observable [20].”
Understanding and improving automated collaborative filtering systems (2000, background): “Johnson & Johnson[43] argue that there is a need for a unified theory of explanation in human-computer interfaces, which would provide predictions for the proper use of content, timing, and patterns of successful explanation.”
The role of transparency in recommender systems (2002, background): “Johnson & Johnson (1993) point out that explanations play a crucial role in the interaction between users and complex systems.”
Aspects of Intelligent Systems Explanation (2013, background): “A unifying theory was recommended by [13] that provided the basis for judging the quality of an explanation.”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “Other studies on interactive dialogues [118, 119, 120, 121, 122] focused on the structure, the language and main components (what pieces of information must be included) of these dialogues.”
How Much Information?: Effects of Transparency on Trust in an Algorithmic Interface (2016, background): “Early research on transparency in complex systems focused on explanations to expose the data or reasoning underlying a system’s output [11].”
Explaining collaborative filtering recommendations (2000, background): “Johnson & Johnson[8] have begun research into the components of a unified theory of explanation in human-computer interfaces.”
Explanation and Justification in Machine Learning : A Survey Or (2017, background): “In expert systems, [Johnson and Johnson, 1993] presented a short survey of accounts of explanation in philosophy, psychology and cognitive science and found that they fall into three categories: associations between antecedent and consequent; contrasts and differences; and causal mechanisms.”
Explainability fact sheets: a framework for systematic assessment of explainable approaches (2019, background): “On the other hand, if the output of a predictive model is not what the users expect, they will contrast the explanation against their mental model to understand the prediction, in which case the explainer should identify and fill in these knowledge gaps [18].”