A Framework for Evaluative Results Integration for Information Retrieval System
Loading...
Date
2013-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Journal of Computer Science and its Application
Abstract
Information Retrieval (IR) systems are evaluated fro two levels, namely the system-centric and user-centric levels. these two levels are made up of three perspectives (aspect) each. the problem with this arrangement is that evaluating the system from any of these perspectives leads to independent evalative results. Therefore, using these results to improve IR systems remains a major challenge. This paper presents an integrative framework for integrating evaluative results from each of the perspectives of the user-centric levels.The integrative framework was used to provide Decision variables (DVs) that were harnessed into a Survey Instrument (SI)used in elliciting data from a total of 250 respondents between years 2010 and 2011. The Crombach Alpha (CA) test was used to test the Dvs. the result of the CA showed that the DVs were internally consistent since their scores range from 0.70 and above, WHile the results indicate that the framework to be proposed would serve its purpose, it also confirm that it needs more testing. The technique of factor analysis was used to test the framework further based on the data elicited using the SI. the purpose was to find out if there is any reasonable correlation between user satisfaction and other factors. The correlation obtained revealed that the use of an integrative agent would assist in harnessing the three perspectives of the user-centric levels. This provided a new way of exploiting the three perspectives at once instead of individually as has been the case. Thus, we propose base on this result that the problem of individual and independent evaluative results that are not usable can be eliminated,
Description
Keywords
Framework, Information Retrieval System, System and user-centric levels, Factor analytic technique, Evaluation and user centric data