J.M. Moreno1, E. Herrera-Viedma2, A.G. Lopez-Herrera2, S. Alonso2, F.J. Cabrerizo3, C. Porcel4

1University of Murcia (SPAIN)
2University of Granada (SPAIN)
3Distance Learning University of Spain (SPAIN)
4University of Jaen (SPAIN)
Background: The importance that e-business is acquiring in this globalised world highlights all the matters related to information retrieval field. Fuzzy Information Retrieval Systems (FIRS) use the potential of the artificial intelligence fuzzy techniques to improve the retrieval activities. The study of these systems belongs to the degree subject Information Management Intelligence Systems at the Faculty of Computer Science (University of Murcia). Some models of FIRS use weighted queries to improve the representation of user information needs and fuzzy connectives to evaluate such queries. We have observed that students have many problems to understand the different semantics that could be associated to the weights of queries together with their respective strategies of query evaluation, so they need to process many examples and compare the results continuously.

Objective: To improve the understanding of FIRS by students of the Information Management Intelligence Systems degree subject, through facilitating their self-learning processes.

Methods: Researchers have found that using computer-supported learning tools may provide students with opportunities to promote their understanding of phenomena in science and to facilitate the visualization of abstract and unobservable concepts. We have searched the Web and peer-reviewed journals for training information retrieval tools, but we have found very few of them, which present several shortcomings, and particularly, it does not exist a FIRS training tool. Therefore, we decided to develop a Web-based student-oriented application to overcome the understanding problems related to the different FIRS’s models. This learning tool is made of three main modules: i.- definition module of test collections; ii.- formulation module of weighted queries; and iii.- a visual execution module of weighted queries. It provides an environment for demonstrating the use and performance of weighted queries with different semantics and their evaluations using different fuzzy connectives. Furthermore, the application provides a feedback on the evaluation of weighted queries by means of visual tools, showing internal aspects through evaluations trees and allowing the visual comparison of the evaluation of different weighted queries.

Results: The use of the learning software tool has offered students the opportunity to see and compare the achieved results of different weighted queries. Students have had the opportunity to choose i.- different semantics (threshold, relative importance, ideal importance, quantitative) to formulate weighted queries; ii.- different fuzzy connectives to evaluate such queries (maximum, minimum, ordered weighted averaging, etc.); and iii.- different expression domains (numerical and fuzzy ordinal linguistic one) to assess weights associated with queries. Our software tool has enabled students to develop self-learning processes on typical FIRS operations and more flexible learning opportunities at their own pace, thus they have got a realistic feeling of the particular FIRS used.

Conclusions: We have to point out that the learning of these complex FIRS has been improved through the use of the student-oriented software tool. The development of self-learning processes has been an important motivational factor that has leaded to increase learning gains. We have achieved enhance students’ learning on FIRS, their motivation has increased, and their marks in final exams have risen.