Using Ontology for Personalized E-Learning in K-12 Education

Using Ontology for Personalized E-Learning in K-12 Education

Petek Askar, Arif Altun, Kagan Kalinyazgan, S. Serkan Pekince
DOI: 10.4018/978-1-60566-782-9.ch018
OnDemand:
(Individual Chapters)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

This chapter introduces the development of a K-12 education ontology for e-learning environments. It presents design and implementation processes, followed by several recommendations for future directions for ontology development. E-learning environments incorporate the notion of semantic Web-based ontologies into their future directions. Semantic Web uses ontologies to show the interconnectedness in a Web environment. Within the concept of semantic mapping, domain ontology is at the core of intelligent e-learning systems. In order to achieve an ontology for K-12 education, the authors propse a domainspecific ontology PoleONTO (Personalized Ontological Learning Environment) with the emphasis on its development and incorporation into an e-learning environment.
Chapter Preview
Top

Introduction

E-learning environments incorporate the notion of semantic Web into their future directions. Semantic Web uses ontologies to show the interconnectedness in a Web environment. Ontologies are being developed in order to decrease the annotated amount of markup and increase the reliability of using computational (intelligent) agents; consequently, a number of ontologies in a variety of domains are being constructed.

Within the concept of semantic mapping, domain ontology is at the core of intelligent e-learning systems. Domain ontologies, explicit formal specifications of the terms in the domain and relations among them (Gruber 1993), cover a common ground vocabulary for researchers and educators who need to share information in a domain. In domain ontology, basic concepts and relations among them are defined and translated into machine-interpretable forms.

In addition to domain-specific ontologies, broad general-purpose ontologies are also being developed. For example, the United Nations Development Program and Dun and Bradstreet collaboratively developed the UNSPSC ontology, which provided a terminology for products and services (i.e., http://www.thegateway.org/) and its controlled vocabulary. The class types include reusable classes (Person, Organization, and Contact), resource object classes (instructional, informational, research), and vocabulary classes (subject categories and terms) (Qin & Hernandes, 2006). Another ontology is Personalized Education Ontology (PEOnto). PEOnto claims to provide learners relevant learning objects based on their individual needs. In PEOnto, five interrelated educational ontologies (curriculum ontology, subject domain ontology, pedagogy ontology, people ontology, and personalized education agents) are being employed (Fok, 2006). In a recent study, Turksoy (2007) developed a tool to share and reuse of learning objects created during activity development process. The author claims that by reusing and sharing the learning objects, instructors use their time efficiently when producing new learning objects. Nevertheless, either no ontology currently exists specific to the K-12 education domain or they are based on using layers of learning processes (for example, problem solving, critical thinking, decision making, etc.) and concepts (for example, number, optics, mole, etc.) simultaneously. Therefore, the purpose of this study is to create a K-12 education ontology by extracting learning processes and concepts to be applied in e-learning platforms.

Key Terms in this Chapter

Skill: The interaction and any processes between persons and concepts.

Formal semantics: The use of natural language as a means for machines to communicate with other machines by using machine-processable models and expressions.

Implicit semantics: The kind that is implicit from the patterns in data and that is not represented explicitly in any strict machine processable syntax.

Powerful (soft) Semantics: The use of statistical analysis of data in order to explore the relationships that are not explicitly stated.

Learning Object: A chunk of elements that can be independently drawn into a momentary assembly in order to create an instructional expectation. These chunks can be reused, re- created and maintained, re-organized and stuck together.

Concept: The solid knowledge articulated across the curriculum.

Complete Chapter List

Search this Book:
Reset