Predictive student model supported by fuzzy-causal knowledge and inference

Alejandro Peña-Ayala, Humberto Sossa-Azuela, Francisco Cervantes-Pérez

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In this article we explore the paradigm of student-centered education. The aim is to enhance the learning of students by the self-adaptation of a Web-based educational system (WBES). The adaptive system's behavior is achieved as a result of the decisions made by a student model (SM). The decision reveals the lecture option most suitable to teach a concept according to the student's profile. Thus, the lecture content is authored from different view points (e.g. learning theory, type of media, complexity level, and user-system interaction degree). The purpose is to tailor several educational options to teach a given concept. Thereby, the SM elicits psychological attributes of the student to describe subjective traits, such as: cognitive, personality, and learning preferences. It also depicts pedagogical properties of the available lecture's options. Moreover, the SM dynamically builds a cognitive map (CM) to set fuzzy-causal relationships among the lecture's option properties and the student's attributes. Based on a fuzzy-causal engine, the SM predicts the bias that a lecture's option exerts on the student's apprenticeship. The conceptual, theoretical, and formal grounds of the approach were tested by a computer implementation of the SM and an experiment. As a result of a field trial, we found that: the average learning acquired by an experimental group of volunteers that used this approach was 17% higher than the average apprenticeship of another equivalent control group, whose lectures were randomly chosen. Thus we conclude that: learning is better stimulated when the delivered lectures account a student's profile than when they ignore it. © 2011 Elsevier Ltd. All rights reserved.
Original languageAmerican English
Pages (from-to)4690-4709
Number of pages4219
JournalExpert Systems with Applications
DOIs
StatePublished - 1 Apr 2012

Fingerprint

student
Students
learning
Adaptive systems
Fuzzy sets
engine
Education
education
Engines

Cite this

@article{bb6063442a984ce58dc9a7b3be780e46,
title = "Predictive student model supported by fuzzy-causal knowledge and inference",
abstract = "In this article we explore the paradigm of student-centered education. The aim is to enhance the learning of students by the self-adaptation of a Web-based educational system (WBES). The adaptive system's behavior is achieved as a result of the decisions made by a student model (SM). The decision reveals the lecture option most suitable to teach a concept according to the student's profile. Thus, the lecture content is authored from different view points (e.g. learning theory, type of media, complexity level, and user-system interaction degree). The purpose is to tailor several educational options to teach a given concept. Thereby, the SM elicits psychological attributes of the student to describe subjective traits, such as: cognitive, personality, and learning preferences. It also depicts pedagogical properties of the available lecture's options. Moreover, the SM dynamically builds a cognitive map (CM) to set fuzzy-causal relationships among the lecture's option properties and the student's attributes. Based on a fuzzy-causal engine, the SM predicts the bias that a lecture's option exerts on the student's apprenticeship. The conceptual, theoretical, and formal grounds of the approach were tested by a computer implementation of the SM and an experiment. As a result of a field trial, we found that: the average learning acquired by an experimental group of volunteers that used this approach was 17{\%} higher than the average apprenticeship of another equivalent control group, whose lectures were randomly chosen. Thus we conclude that: learning is better stimulated when the delivered lectures account a student's profile than when they ignore it. {\circledC} 2011 Elsevier Ltd. All rights reserved.",
author = "Alejandro Pe{\~n}a-Ayala and Humberto Sossa-Azuela and Francisco Cervantes-P{\'e}rez",
year = "2012",
month = "4",
day = "1",
doi = "10.1016/j.eswa.2011.09.086",
language = "American English",
pages = "4690--4709",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Ltd",

}

Predictive student model supported by fuzzy-causal knowledge and inference. / Peña-Ayala, Alejandro; Sossa-Azuela, Humberto; Cervantes-Pérez, Francisco.

In: Expert Systems with Applications, 01.04.2012, p. 4690-4709.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Predictive student model supported by fuzzy-causal knowledge and inference

AU - Peña-Ayala, Alejandro

AU - Sossa-Azuela, Humberto

AU - Cervantes-Pérez, Francisco

PY - 2012/4/1

Y1 - 2012/4/1

N2 - In this article we explore the paradigm of student-centered education. The aim is to enhance the learning of students by the self-adaptation of a Web-based educational system (WBES). The adaptive system's behavior is achieved as a result of the decisions made by a student model (SM). The decision reveals the lecture option most suitable to teach a concept according to the student's profile. Thus, the lecture content is authored from different view points (e.g. learning theory, type of media, complexity level, and user-system interaction degree). The purpose is to tailor several educational options to teach a given concept. Thereby, the SM elicits psychological attributes of the student to describe subjective traits, such as: cognitive, personality, and learning preferences. It also depicts pedagogical properties of the available lecture's options. Moreover, the SM dynamically builds a cognitive map (CM) to set fuzzy-causal relationships among the lecture's option properties and the student's attributes. Based on a fuzzy-causal engine, the SM predicts the bias that a lecture's option exerts on the student's apprenticeship. The conceptual, theoretical, and formal grounds of the approach were tested by a computer implementation of the SM and an experiment. As a result of a field trial, we found that: the average learning acquired by an experimental group of volunteers that used this approach was 17% higher than the average apprenticeship of another equivalent control group, whose lectures were randomly chosen. Thus we conclude that: learning is better stimulated when the delivered lectures account a student's profile than when they ignore it. © 2011 Elsevier Ltd. All rights reserved.

AB - In this article we explore the paradigm of student-centered education. The aim is to enhance the learning of students by the self-adaptation of a Web-based educational system (WBES). The adaptive system's behavior is achieved as a result of the decisions made by a student model (SM). The decision reveals the lecture option most suitable to teach a concept according to the student's profile. Thus, the lecture content is authored from different view points (e.g. learning theory, type of media, complexity level, and user-system interaction degree). The purpose is to tailor several educational options to teach a given concept. Thereby, the SM elicits psychological attributes of the student to describe subjective traits, such as: cognitive, personality, and learning preferences. It also depicts pedagogical properties of the available lecture's options. Moreover, the SM dynamically builds a cognitive map (CM) to set fuzzy-causal relationships among the lecture's option properties and the student's attributes. Based on a fuzzy-causal engine, the SM predicts the bias that a lecture's option exerts on the student's apprenticeship. The conceptual, theoretical, and formal grounds of the approach were tested by a computer implementation of the SM and an experiment. As a result of a field trial, we found that: the average learning acquired by an experimental group of volunteers that used this approach was 17% higher than the average apprenticeship of another equivalent control group, whose lectures were randomly chosen. Thus we conclude that: learning is better stimulated when the delivered lectures account a student's profile than when they ignore it. © 2011 Elsevier Ltd. All rights reserved.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=84855877075&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=84855877075&origin=inward

U2 - 10.1016/j.eswa.2011.09.086

DO - 10.1016/j.eswa.2011.09.086

M3 - Article

SP - 4690

EP - 4709

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -