Christos Pierrakeas

ANALYZING STUDENT PERFORMANCE IN DISTANCE LEARNING WITH GENETIC ALGORITHMS AND DECISION TREES

Students that enroll in the undergraduate program on informatics at the Hellenic Open University (HOU) demonstrate significant difficulty in advancing beyond the introductory course. We have embarked in an effort to analyze their academic performance throughout the academic year, as measured by homework assignments, and attempt to derive short rules that explain and predict success or failure in the final exams. In this paper we review previous approaches, compare them with genetic algorithm-based induction of decision trees, and argue why our approach has a potential for developing into an alert tool.

An Ontology Model for Building, Classifying and Using Learning Outcomes

Learning outcomes are statements that should accompany any type of educational material intended for lifelong learning. These statements deliver important information, which works as an indicator for students in the process of learning. However, in order for this information to be further utilizable within the context of intelligent e-learning applications, a more fine-grained definition and structure should be adopted. Having these in mind, we initially assign a strict and rather technical definition for the notion of learning outcomes, which is fully aligned, though, with their educational purpose. We then propose an ontological model for their representation and classification, which fully adheres to this definition. Our ultimate goal is to provide the mean for exploiting all aspects of knowledge implied by such statements within intelligent applications. To bear out this possibility, we apply our model to a selected piece of educational material provided by the Hellenic Open University.

Online Collaboration Environments in Telemedicine Applications of Speech Therapy

The use of telemedicine in speech and language pathology provides patients in rural and remote areas with access to quality rehabilitation services that are sufficient, accessible, and user-friendly leading to new possibilities in comprehensive and long-term, cost-effective diagnosis and therapy. This paper discusses the use of online collaboration environments for various telemedicine applications of speech therapy which include online group speech therapy scenarios, multidisciplinary clinical consulting team, and online mentoring and continuing education

Evaluating and improving educational Material and tutoring aspects of distance learning systems

This paper presents the approach followed for the evaluation of the educational system of the Informatics Course in the Hellenic Open University. Emphasis is placed on the evaluation method itself, which is general enough to be applied in similar evaluation cases, and on the discussion of the lessons learned during this evaluation. The presented method can be used for the improvement of the two major components of distance learning systems: the educational material and the role of the tutor. The paper discusses the conclusions drawn from the evaluation procedure and the actions taken towards improvement, aiming to serve as an example for similar attempts and share experiences in the field of distance education.

An Ontology-Based Model for Student Representation in Intelligent Tutoring Systems for Distance Learning

An Intelligent Tutoring System (ITS) offers personalized education to each student in accordance with his/her learning preferences and his/her background. One of the most fundamental components of an ITS is the student model, that contains all the information about a student such as demographic information, learning style and academic performance. This information enables the system to be fully adapted to the student. Our research work intends to propose a student model and enhance it with semantics by developing (or via) an ontology in order to be exploitable effectively within an ITS, for example as a domain-independent vocabulary for the communication between intelligent agents. The ontology schema consists of two main taxonomies: (a) student’s academic information and (b) student’s personal information. The characteristics of the student that have been included in the student model ontology were derived from an empirical study on a sample of students.

Modeling the characteristics of a learning object for use within e-learning applications

Educational content plays a significant role in the process of delivering knowledge, thats why it needs to be designed carefully, following designated principles. Learning Objects (LOs) constitute a novel approach in the educational contents organization, bearing features that if effectively used could lead to enhanced e-learning services. What is missing from literature, though, is a common agreement about the LOs attributes and structure. For this reason, we initially try to specify the main characteristics of a LO and determine its functionality, especially in the context of distance education. Having realized its fundamental role in the instructional design process, we make explicit its correlation with educational objectives and other aspects of learning. Finally, in an attempt to capture all LOs characteristics and make them utilizable by e-learning applications, we propose a metadata schema, reflecting all features of a LO, as described in this work.

Modeling the knowledge domain of the java programming language as an ontology

Java is a very popular programming language and many study programs in Informatics worldwide include courses particularly designed for its learning. It is considered as the best paradigm for introducing students with object-oriented programming and concepts. Considering Javas popularity, we initially make an attempt to model this language by using a quite expressing and rich knowledge representation structure, like is ontology. Our aim is to capture the semantics of Java concepts in a way that would render them utilizable by intelligent e-learning applications. Because the construction of an ontology is not an easy task, we follow very specific steps when building the Java ontology. We then take advantage of an already implemented model describing the structure of learning outcomes and combine it with our ontology, with a view to offer a more effective way in organizing the course of Java in the Hellenic Open University.

Creating a LO Metadata Profile for Distance Learning: An Ontological Approach

The importance of Learning Objects (LOs) in the learning process - especially in the case of distance education - has been underlined significantly in the literature. The ability of administrating LOs in terms of accessibility, reusability and interoperability seems to be ensured by adopting an appropriate metadata schema which fully and adequately describes them. Several metadata standards have been developed such as DC (Dublin Core) and IEEE-LOM. In the context of our work, we explore them and conclude that none of these standards does completely meet the requirements of distance learning material. Therefore, we propose a new metadata schema that is actually an application profile of the widely adopted IEEE LOM and has special orientation in distance education. We also enrich this subset with some additional attributes that represent concepts like learning outcomes. Then, we create an ontological representation of this new educational schema with a view to improving the potential of LOs’ discovery and retrieval within an intelligent e-learning system.

Using Genetic Algorithms and Decision Trees for a posteriori Analysis and Evaluation of Tutoring Practices based on Student Failure Models

Many students who enrol in the undergraduate program on informatics at the Hellenic Open University (HOU) fail the introductory course exams and drop out. We analyze their academic performance, derive short rules that explain success or failure in the exams and use the accuracy of these rules to reflect on specific tutoring practices that could enhance success.

Assessing the Quality of Web-sites used in Higher Open Distance Education Courses

The purpose of this study is to present the experiences from the quality assessment of the educational web sites of two modules of the computer science curriculum in the Hellenic Open University. This paper presents the quality assessment methods currently available, discusses their requirements and their application, as well as the problems that might arise during the assessment process and possible solutions. It also presents results and lessons learned from the application of representative methods. Thus, this paper aims at serving as an experience report that could be of use to educational institutes that intend to conduct similar quality assessments. The surveys presented in this paper show that the inquiry methods, i.e. the methods that are most frequently used in similar quality assessment cases, can offer a general overview of the educational web site quality, but fail to indicate particular problems. On the other hand, the inspection and testing methods, although useful for highlighting particular problems, cannot offer an overview of the educational web site quality as perceived by the users. Therefore, for obtaining better results it is recommended that the assessment methodology selected by an educational institute should combine both methods conducted in a laboratory—such as the inspection and testing methods—and inquiry methods.