Article Preview
Top1. Introduction
Electronic learning (e-Learning) is a facility where students learn related course or other types of materials via online computer systems. Moreover, e-learning has proved to be an effective way of delivering materials to unreachable students and the success stories of e-learning conferences and e-learning community speak for the glory. One of the main advantages of e-Learning technology is that it can facilitate adaptive learning. In this scenario, instructors can dynamically revise and deliver instructional materials in accordance with learners’ current progress. Since, adaptive teaching and learning helps to know about learners, a priori or through interactions it helps to alter the learning experience, with the aim of improving learners’ success and satisfaction.
Ontology in e-learning is helpful to create a set of similar group students connected with different types of relations. Each group can include a set of related documents for understanding effectively. Construction of such ontology from a given corpus can be a very time consuming task for the lecturer. In order to get a feeling of what the group in the corpus are, what the relations between topics are and to assign each document to some certain topics. The lecturer has to go through all the documents and process them manually. In order to overcome a new approach is proposed in this paper with special features by building the ontology automatically. Using this system it is possible to visualize similar group of students and to give the material to the student based on this result. So, this work aims at assisting the learners and lecturers in a fast way by automatic construction of the ontology from a large document collection for effective decision making.
Generally, e-Learning technologies can support automatic analysis of learners’ progress in terms of the knowledge structures they have acquired. In this work, a methodology for automatically constructing concept maps on the subject learnt by a student to characterize learners’ understanding for a particular topic has been designed and implemented. Using this system, teacher’s can conduct adaptive teaching and learning based on the learners’ knowledge structures as reflected on the concept maps. In particular, the concept map generation mechanism implemented in this work is underpinned by a context-sensitive text mining method and a fuzzy domain ontology extraction. Concept maps are useful to generate ontology, since ontology provides an effective representation to represent concepts and the semantic relationships among concepts. Moreover, the ontology proposed in this paper facilitates human and computer interactions and it can be easily expressed by using formal semantic markup languages such as RDF and OWL. This system has been implemented using Java, Protégé’s, Wordnet and eclipse.
The two major objectives of this paper are the development of a novel fuzzy domain ontology extraction method as proposed in (Lau et al., 2009) by implementing it for e-learning domain and to provide suitable learning materials and teaching methodologies to each group of students. Although some learning techniques have been proposed in the past for automatic or semiautomatic extraction of domain ontology, those methods did not consider the students level logically and hence enhancement are provided in this work to provide different types of learning contents to different groups of students.
Moreover, this work provides facilities to apply the context-sensitive text mining method and the fuzzy domain ontology extraction algorithm to automatically generate concept maps to reveal the knowledge structures of students who are engaged in e-Learning. As a result, instructors can conduct adaptive teaching and learning based on the information disclosed on the ontology maps.
The performance of the learners in E-learning environments is greatly influenced by the nature of the posted E-learning contents. In such a scenario, the performance of the learners can be enhanced by posting the suitable E-learning contents to the learners based on their learning styles. However, predicting the learning styles needs complete knowledge about the learners past and present characteristics. In addition, the excellence of the E-Learning learners can be improved by recommending suitable E-Learning contents available in the E-Learning servers. This kind of recommendation can be done as an additional feature for excellence and it is based on investigating their learning styles. The learning styles are to be predicted carefully, since the psychological balance differs from one individual to another. Moreover, the knowledge about the E-Learning learners that used for learning style prediction is also uncertain in nature.