Mapping Goals and Kinds of Explanations to the Knowledge Containers of Case-Based Reasoning Systems

Roth–Berghofer, Thomas; Cassens, Jörg

doi:10.1007/11536406_35

Cited by 27 publications

(19 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our goal is therefore to integrate these perspectives further and combine them with other steps of the CBR system lifecycle [6].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

User Aspects of Explanation Aware CBR Systems

Cassens

2005

Human-Computer Interaction - INTERACT 2005

Self Cite

View full text Add to dashboard Cite

Abstract. This paper addresses the problem of embedding explanationaware intelligent systems into a workplace environment. We outline an approach with three different perspectives, focusing on the work process as a whole as well as user interaction from an interface and a system view. The theoretical background consists of Actor Network Theory, Semiotics, and Activity Theory. We further propose to integrate this workplace analysis into a design process for knowledge-intensive and explanationaware Case-Based Reasoning systems.

show abstract

“…Our goal is therefore to integrate these perspectives further and combine them with other steps of the CBR system lifecycle [6].…”

Section: Discussionmentioning

confidence: 99%

“…We are therefore in need of methodologies which can describe the workplace environment in which the system is going to be used on the human-computer interaction level. This analysis is then integrated into the design process as a whole, as described in [6].…”

Section: Introductionmentioning

confidence: 99%

User Aspects of Explanation Aware CBR Systems

Cassens

2005

Human-Computer Interaction - INTERACT 2005

Self Cite

View full text Add to dashboard Cite

show abstract

“…Earlier work by Roth-Berghofer and others has coupled explanation goals with the knowledge containers of case-based reasoning systems [23]. Having an explicit representation of explanation goals helps in identifying requirements for the knowledge containers, easing the way from a specification document to the structure and content of the knowledge containers.…”

Section: Analysing the Existing Applicationmentioning

confidence: 99%

Modelling with Problem Frames: Explanations and Context in Ambient Intelligent Systems

Kofod-Petersen

Cassens

2011

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. When designing and implementing real world ambient intelligent systems we are in need of applicable information systems engineering methods. The tools we find in the intelligent systems area focus on the knowledge engineering parts, whereas traditional software engineering techniques are usually not designed with the peculiarities of intelligent systems design in mind. This holds in particular for explanation-aware intelligent systems. This work looks at problem frames for explanations and investigates how problem frames can be used to elicit, analyse, and specify these specific requirements. The point of departure is an existing ambient intelligent information system for the hospital ward domain. The work presented here analyses how such a system can be redesigned with a focus on explanation-awareness.

show abstract

“…Sørmo et al [12] suggest a set of explanation goals addressing transparency, justification, relevance, conceptualisation, and learning. In [9], Roth-Berghofer and Cassens outline the combination of both, goals and kinds of explanations, in the context of Case-Based Reasoning, and examine the contribution of the four CBR knowledge containers for modelling necessary knowledge. In the following we take up this idea and cast it on the field of data mining.…”

Section: Goals and Kinds Of Explanationsmentioning

confidence: 99%

The Mining and Analysis Continuum of Explaining Uncovered

Atzmueller

Roth–Berghofer

2010

Research and Development in Intelligent Systems XXVII

View full text Add to dashboard Cite

The result of data mining is a set of patterns or models. When presenting these, all or part of the result needs to be explained to the user in order to be understandable and for increasing the user acceptance of the patterns. In doing that, a variety of dimensions for explaining needs to be considered, e.g., from concrete to more abstract explanations. This paper discusses a continuum of explaining for data mining and analysis: It describes how data mining results can be analysed on continuous dimensions and levels.

show abstract

Mapping Goals and Kinds of Explanations to the Knowledge Containers of Case-Based Reasoning Systems

Cited by 27 publications

References 20 publications

User Aspects of Explanation Aware CBR Systems

User Aspects of Explanation Aware CBR Systems

Modelling with Problem Frames: Explanations and Context in Ambient Intelligent Systems

The Mining and Analysis Continuum of Explaining Uncovered

Contact Info

Product

Resources

About