ORIEB, A CRS FOR ACADEMIC ORIENTATION USING QUALITATIVE ASSESSMENTS Emilio J. Castellano, Luis Martínez Universidad de Jaén Campus de las Lagunillas s/n, 23021. Jaén ABSTRACT Collaborative Recommender Systems (CRS) are very useful tools that help people to select items in a huge search space, based on the idea that people with similar taste of preferences in an topic make similar decisions concerning to that topic. There are many commercial applications that show the utility of these systems. In this contribution we shall introduce OrieB, a CRS working in the Academic Orientation domain in order to support advisors helping students of secondary school to make decisions about their academic future. OrieB will use students’ marks as input data in order to suggest their academic possibilities by providing qualitative recommendations based on the fuzzy linguistic approach. KEYWORDS Academic Collaborative Recommender System, Qualitative Information. 1. INTRODUCTION When students reach certain level in their academic journey, they need to make decisions about their academic or professional future. Many countries have created one figure, called advisor, whose main task is to guide students when they face up these decision situations. But advisors have to manage many students and often it is hard for them to give optimum advices because there are many variables concerning the orientation task, including students’ expedient. We think that the use of Collaborative Filtering (CF) using the marks obtained by the students to generate groups of similar students and compute recommendations based on those elections made by previous students could be very useful for academic orientation. Moreover we consider that marks represent more than simple and single quantifiers. Marks are given by teachers (experts) and set up them taking into account a set of features, skills, knowledge, etc. that a student have in any specific subject; besides, marks reflect also information about student preferences. It is known that whenever a student likes a subject, she usually does her best in it. Any educational system presents the following features: • There are students that course subjects. • There are usually several kinds of subjects: core subjects, elective subjects, and vocational subjects. • There may be vocational programs, built with groups of subjects having same professional scope. • Applying an evaluation protocol to the pair subject-student teachers obtain a single value called mark. Taking into account these assertions a Collaborative Recommender System (CRS) (Schafer et al., 2001, Pazzani, 1999) for Academic Orientation computes recommendations by predicting marks using Collaborative Filtering (CF) and analyzing those predictions by grouping them based on subject topics, programs, grades, etc., could be a valuable system in order to support academic orientation aims. Following the idea of CRS, we studied its performance in the student guidance domain, in their subject and academic profile choices during their different stages at high/secondary school and University (Castellano et al., 2007). Then we will present OrieB, a CRS which uses students’ marks to generate a profile in order to classify them in different groups of similar students concerning their skills and tastes that will be utilized to build recommendations that support advisors guiding students in their academic decisions. Initially the recommendations computed by OrieB were numerical values, however in fact the aim we chase in this system it is a value to support advisors in their orientation duties, then the use of precise ISBN: 978-972-8924-58-4 © 2008 IADIS 38