Evaluation of Concept Lattices in a Web-Based Mail Browser
Concept lattices assist human understanding in three ways: firstly, by collecting formal concepts that contain maximal sets of objects with shared attributes; secondly, the relatedness of concepts is revealed by providing a hierarchy of formal concepts in the information space. Finally, the concept lattice (drawn as a line diagram) reveals inferences that can automatically derive association rules. Therefore, a major hypothesis of the application of concept lattices is that they visually assist in understanding the structure of information contained within an information space. However, there has been little in the way of empirical tests to substantiate this hypothesis. This paper describes the process and results of a usability evaluation for a program called Mail-Strainer, a Web-based variant of the Mail-Sleuth program, which in turn is based on the Conceptual Email Manager (Cem).
KeywordsConcept Lattice Fold Structure Formal Concept Analysis Line Diagram Test Script
Unable to display preview. Download preview PDF.
- 1.Bice, B.: Building a web mail server with squirrelmail. SysAdmin Magazine: The Journal for Uniz and Linux System Administrators 11(7) (2002), http://www.sysadminmag.com/articles/2002/0207/
- 3.Carpineto, C., Romano, G.: A lattice conceptual clustering system and its application to browsing retrieval. Machine Learning 24(2), 95–122 (1996)Google Scholar
- 4.Carpineto, C., Romano, G.: Concept Data Processing: Theory and Practice. Wiley, Chichester (2004)Google Scholar
- 7.Cole, R., Eklund, P., Stumme, G.: Document retrieval for email search and discovery using formal concept analysis. Journal of Experimental and Theoretical Artificial Intelligence 17(3), 257–280 (2003)Google Scholar
- 10.Eklund, P., Wormuth, B.: Restructuring help systems using formal concept analysis. In: Ganter, B., Godin, R. (eds.) Proceedings of the 3rd International Conference on Formal Concept Analysis - ICFCA 2004. Springer, Heidelberg (February 2004)Google Scholar
- 12.Kirakowski, K., Corbett, M.: Effective Methodology for the Study of HCI. Elsevier Science, Amsterdam (1990)Google Scholar