User centred evaluation of a recommendation based image browsing system

Leelanupab, T., Hopfgartner, F. and Jose, J.M. (2009) User centred evaluation of a recommendation based image browsing system. In: The 4th Indian International Conference on Artificial Intelligence, Tumkur (near Bangalore), India, 16-18 December 2009, pp. 1-16.

[img] Text
5959.pdf

1MB

Publisher's URL: http://www.iiconference.org/

Abstract

In this paper, we introduce a novel approach to recommend images by mining user interactions based on implicit feedback of user browsing. The underlying hypothesis is that the interaction implicitly indicates the interests of the users for meeting practical image retrieval tasks. The algorithm mines interaction data and also low-level content of the clicked images to choose diverse images by clustering heterogeneous features. A user-centred, task-oriented, comparative evaluation was undertaken to verify the validity of our approach where two versions of systems { one set up to enable diverse image recommendation { the other allowing browsing only { were compared. Use was made of the two systems by users in simulated work task situations and quantitative and qualitative data collected as indicators of recommendation results and the levels of user's satisfaction. The responses from the users indicate that they nd the more diverse recommendation highly useful.

Item Type:Conference Proceedings
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Jose, Professor Joemon and Hopfgartner, Dr Frank
Authors: Leelanupab, T., Hopfgartner, F., and Jose, J.M.
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
College/School:College of Science and Engineering > School of Computing Science
College of Arts & Humanities > School of Humanities > Information Studies
Copyright Holders:Copyright © 2009 The Authors
First Published:First published in proceedings of the 4th Indian International Conference on Artificial Intelligence
Publisher Policy:Reproduced with permission of the authors.

University Staff: Request a correction | Enlighten Editors: Update this record