Year: 2016
Type: conference-paper
Abstract: In the research field of User Modeling, Adaptation and Personalization there is a strong focus on comparative evaluation. In this discussion paper we as ourselves when it makes sense to perform such evaluation and also when it is complete nonsense. We argue that especially for adaptive systems (and not applications) the typical comparitive evaluations with groups of end-users make no sense. We also argue that for applications it is difficult to perform a meaningful evaluation because it is hard to find something to compare the (use of the) application with.
Source: TU/e Research Portal
Author: Paul De Bra
Language: English
Subfield: Human-Computer Interaction
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2578258836