Ricardo Conejo

User Modeling, Adaption and Personalization

This book constitutes the proceedings of the third annual conference under the UMAP title, adaptation, which resulted from the merger in 2009 of the successful biannual User Modeling (UM) and Adaptive Hypermedia (AH) conference series, held on Girona, Spain, in July 2011. The 27 long papers and 6 short papers presented together with15 doctoral consortium papers, 2 invited talks, and 3 industry panel papers were carefully reviewed and selected from 164 submissions. The tutorials and workshops were organized in topical sections on designing adaptive social applications, semantic adaptive social Web, and designing and evaluating new generation user modeling.

Self-assessment in a feasible, adaptive web-based testing system

Adaptive testing systems generate tests for assessment that are tailored to each student. In these tests, students are assessed through a process that uses Item Response Theory (IRT), a well-founded psychometric theory. This theory is responsible for estimating student knowledge, determining the next question that must be posed at each moment, and deciding test finalization. System of Intelligent Evaluation Using Tests for Teleeducation (SIETTE) is a Web-based environment for generating and constructing adaptive tests. In SIETTE, teachers can create tests for self-assessment. In this kind of test, questions are posed one by one, and the correction of each question is shown immediately after the students answer. Along with this correction, and in terms of the students answer, feedback is provided. Feedback consists of pieces of knowledge that help students detect misconceptions or reinforce concepts correctly learned. Furthermore, hints can be included when questions are posed to supply students with some kind of help or explanation about the stem. As a result, this kind of test can be used not just for assessment, but also for instructional purposes. The first goal of this paper is to show how SIETTE can be used for instructional purposes, by combining adaptive student self-assessment test questions with feedback and hints. This paper also shows that the Web is a feasible platform for the generation of adaptive tests, supporting the use of SIETTE for this purpose.

A Model for Student Knowledge Diagnosis Through Adaptive Testing

This work presents a model for student knowledge diagnosis that can be used in ITSs for student model update. The diagnosis is accomplished through Computerized Adaptive Testing (CAT). CATs are assessment tools with theoretical background. They use an underlying psychometric theory, the Item Response Theory (IRT), for question selection, student knowledge estimation and test finalization. In principle, CATs are only able to assess one topic for each test. IRT models used in CATs are dichotomous, that is, questions are only scored as correct or incorrect. However, our model can be used to simultaneously assess multiple topics through content-balanced tests. In addition, we have included a polytomous IRT model, where answers can be given partial credit. Therefore, this polytomous model is able to obtain more information from student answers than the dichotomous ones. Our model has been evaluated through a study carried out with simulated students, showing that it provides accurate estimations with a reduced number of questions.

Adaptive testing for hierarchical student models

This paper presents an approach to student modeling in which knowledge is represented by means of probability distributions associated to a tree of concepts. A diagnosis procedure which uses adaptive testing is part of this approach. Adaptive tests provide well-founded and accurate diagnosis thanks to the underlying probabilistic theory, i.e., the Item Response Theory. Most adaptive testing proposals are based on dichotomous models, where he student answer can only be considered either correct or incorrect. In the work described here, a polytomous model has been used, i.e., answers can be given partial credits. Thus, models are more informative and diagnosis is more efficient. This paper also presents an algorithm for estimating question characteristic curves, which are necessary in order to apply the Item Response Theory to a given domain and hence must be inferred before testing begins. Most prior estimation procedures need huge sets of data. We have modified preexisting procedures in such a way that data requirements are significantly reduced. Finally, this paper presents the results of some controlled evaluations that have been carried out in order to analyze the feasibility and advantages of this approach.

Introducing prerequisite relations in a multi-layered bayesian student model

In this paper we present an extension of a previously developed generic student model based on Bayesian Networks. A new layer has been added to the model to include prerequisite relationships. The need of this new layer is motivated from different points of view: in practice, this kind of relationships are very common in any educational setting, but also their use allows for improving efficiency of both adaptation mechanisms and the inference process. The new prerequisite layer has been evaluated using two different experiments: the first experiment uses a small toy example to show how the BN can emulate human reasoning in this context, while the second experiment with simulated students suggests that prerequisite relationships can improve the efficiency of the diagnosis process by allowing increased accuracy or reductions in the test length.

An Empirical Approach to On-Line Learning in SIETTE

SIETTE is a web-based evaluation tool that implements CAT theory. With the help of a simulation program, different empirical experiments have been performed with SIETTE with two different goals: a) to study the influence of the parameters of characteristic item curves and selection criteria in test length and accuracy; and b) to study different learning strategies for these parameters. The results of the experiments are shown and interpreted.

METIOREW: An Objective Oriented Content Based and Collaborative Recommending System

The size of Internet has been growing very fast and many documents appear every day in the Net. Users find many problems in obtaining the information that they really need. In order to help users in this task of finding relevant information, recommending systems were proposed. They give advice using two methods: the content-based method that extracts information from the already evaluated documents by the user in order to obtain new related documents; the collaborative method that recommends documents to the user based on the evaluation by users with similar information needs. In this paper we analyze some existing Web recommending systems and identify some problems which we try to solve in our system METIOREW.

A Learner Model in a Distributed Environment

A learner model must store all the relevant information about a student, including knowledge and attitude. This paper proposes a domain independent learner model based in the classical overlay approach that can be used in a distributed environment. The model has two sub-models: the learner attitude model, where the static information about the user is stored (user’s personal and technical characteristics, user’s preferences, etc.) and the learner knowledge model, where the user’s knowledge and performance is stored. The knowledge model has four layers: estimated, assessed, inferred by prerequisite and inferred by granularity. The learner model is used as a part of the MEDEA system, so the first and second layers are updated directly by the components of MEDEA and the third and fourth are updated by Bayesian inference.

Simultaneous Evaluation of Multiple Topics in SIETTE

SIETTE is an efficient web-based implementation of a Computer Adaptive Test. The inference machine used is based on Item Response Theory. New enhances in the evaluation mechanisms, question selection and finalization criteria have been introduced. New evaluation mechanism allows giving structured knowledge estimation about all topics evaluated in a test. Question selection criteria are able to automatically select a balanced number of items from all topics, so teachers do not need to accomplish this task manually. This paper shows that SIETTE can successfully be integrated into web-based Intelligent Tutoring Systems with structured curriculum, in order to make initial estimations of the students knowledge level, or even to update the students model after his exposition to instructional components.

INGRID: a web service tool for hierarchical open learner model visualization

This paper presents a tool to visualize open learner models. The tool is domain independent and is freely available as a web service. It can be easily integrated with any existing web-based learning environment.