Catálogo de publicaciones - libros

In this study, a tutoring system with a learner-initiating instruction strategy is proposed to help learners solve digital logic problems that they input to the system. After the system comprehends the problem inputted by the learner and determines the category of the problem, the system produces a solution plan for the learner. The learner solves the problem by following the plan step by step. After that, the system diagnoses the learner’s answer when s/he executes a plan. If the learner’s answer is incorrect, the system provides hints for the learner to revise the answer. Empirical evaluation results indicate that the system is effective in tutoring digital logic problem.

Reflection is critically important for time-constrained training simulations that do not permit extensive tutor-student interactions during an exercise. Here, we describe a reflective tutoring system for a virtual human simulation of negotiation. The tutor helps students review their exercise, elicits where and how they could have done better, and uses explainable artificial intelligence (XAI) to allow students the chance to ask questions about the virtual human’s behavior.

Building a mapping between items and their related knowledge components, while difficult and time consuming, is central to the task of developing affective intelligent tutoring systems. Improving performance on this task by creating a semi-automatic skill encoding system would facilitate the development of such systems. The goal of this project is to explore techniques involved in text classification to the end of improving the time required to correctly tag items with their associated skills.

The Self-Assessment Tutor (SAT) is an add-on component to Cognitive Tutors that supports self-assessment in four steps: , and . The SAT encourages students to self-assess their ability spontaneously while problem solving, and to use help resources accordingly. For that reason its episodes precede the students’ work with the Cognitive Tutor, which itself remains unchanged. The SAT offers detailed feedback and help function to support the Self-Assessment process. A complementary instruction is given to students before working with the SAT. We hypothesize that working with the SAT will encourage students to self-assess on subsequent problems requiring similar skills, and thus will promote learning. A classroom evaluation of SAT is currently in progress.

This paper presents a within-subject, randomized experiment to compare automated interventions for teaching vocabulary to young readers using Project LISTEN’s Reading Tutor. The experiment compared three conditions: no explicit instruction, a quick definition, and a quick definition plus a post-story battery of extended instruction based on a published instructional sequence for human teachers. A month long study with elementary school children indicates that the quick instruction, which lasts about seven seconds, has immediate effects on learning gains that did not persist. Extended instruction which lasted about thirty seconds longer than the quick instruction had a persistent effect and produced gains on a posttest one week later.

The aim of our research is to realize a system for supporting English composition in second language learning which allows learners to compose some sentences and gain appropriate awareness of their errors in the sentences with indirect information from the system. This paper proposes a method when and how the system provides stimuli to the learners, describes its implementation briefly, and reports validity of the method. We adopt a method of visualizing learners’ errors as indirect information for the learners.

This study presents an assessment agent that models collaborative learning as multi-issue agent negotiation using fuzzy constraints for peer assessment. The proposed method aggregates student marks to avoid the subjective judgments and unfair assessments. Experimental results indicated that students and instructors generally acknowledged the peer assessment as a valuable process for enhancing student critical thinking skills and improving learning performance.

Recently, a lot of new educational games have been exploited rapidly due to the advance of information technology. However, it is unpractical for instructors to apply the existing educational games as they intend. In this paper, we propose an educational authoring tool called (Template-based Entertainment Learning Authoring Tool) for an individualized learning on the web, which can be easily developed by instructors. In general, it’s known that game-style learning has the advantage in increasing the learner’s interest and immersiveness. However, it’s not difficult to find out that if someone has completed certain learning game, he/she tends to lose the interest on the game and the game becomes a useless one. To tackle the problem, we design and develop a specific authoring tool, which enables instructors to develop the various educational games according to the levels of learners and learning contents.

In this document a platform for the development of ITSs is presented. The objective of this architecture is to provide a tutoring platform with a modular structure suitable to accommodate different sequencing paradigms through a common functional interface. The platform has been tested with positive results.

This paper presents the design of an intelligent software architecture called (LVOT) to facilitate the definition, registration and delivery of objects in a (GeLEnv). The research work brings our initial explorations towards the definition and use of simple and more complex learning objects in cooperative environments. We use a top-down analysis process [4] to describe GeLEnv models. Our architecture serves to statically and dynamically generate learning objects using a special purpose registry and, two core functional engines. Basic, composite and cooperative LVO structures can be defined and registered using the first engine. The second engine intelligently processes these structures to provide the learning resources to the final users of our LVOT platform.