SciELO Suggester: An intelligent support tool for cataloging library resources

Abstract

Existing cataloging interfaces are designed to reduce the bottleneck of creating, editing, and refining bibliographic records by offering a convenient framework for data entry. However, the cataloger still has to deal with the difficult task of deciding what information to include. The SciELO Suggester system is an innovative tool developed to overcome certain general limitations encountered in current mechanisms for entering descriptions of library records. The proposed tool provides useful suggestions about what information to include in newly created records. Thus, it assists catalogers with their task, as they are typically unfamiliar with the heterogeneous nature of the incoming material. The suggester tool applies case-based reasoning to generate suggestions taken from material previously cataloged in the SciELO scientific electronic library. The system is implemented as a web service and it can be easily used by installing an add-on for the Mozilla Firefox browser. The tool has been evaluated through a human-subject study with catalogers and through an automatic test using a collection consisting of 5742 training examples and 120 test cases from 12 different subject areas. In both experiments the system has shown very good performance. These evaluations indicate that the use of case-based reasoning provides a powerful alternative to traditional ways of identifying subject areas and keywords in library resources. In addition, a heuristic evaluation of the tool was carried out by taking as a starting point the Sirius heuristic-based framework, resulting in a very good score. Finally, a specially designed cognitive walk was completed with catalogers, providing additional insights into the strengths and weaknesses of the tool.