E-learning, which typically means using a computer for a learning activity or in a learning environment, was proposed in the nineteenth century. A learning management system (LMS) was widely applied in the educational field to report, administer, and document courses. In the twentieth century, the development of educational technology was focused on computer-mediated communication between teachers and learners. In the twenty-first century, with the introduction of information and communications technology (ICT), educational technology has turned to cloud-based technology (see Figure 1-1).
Figure 1-1 The evolution of educational technology.
Cloud-based technology has evolved dramatically in the 10 years, and this technology has become a critical tool in today’s world of education. Cloud educational technology has benefits that include increasing accessibility, reducing information technology (IT) and infrastructure costs, enabling collaboration, and allowing learners
new educational technologies such as online games, massive online open courses (MOOCs), and cloud data mining have been gaining popularity. MOOCs provide an open-access curriculum to an unlimited number of learners and integrate social networking and interactive user forums. In MOOCs, learners can plan their participation according to their learning interests, learning goals, and prior knowledge. The present study investigates the influence that learning-style preferences have on learners’
intentions to use MOOCs.
In a diverse learning environment, there are no fixed learning paths that are appropriate for all learners. Therefore, personalized learning is an important research issue for an LMS. Many researchers have focused on developing cloud-based personalized learning techniques that can be adapted to an individual’s needs. The present study aims at enhancing learning efficiency and fit individual’s needs. The study focuses on assessing the effects of different materials on learning performance and cognition, and the use of a mining algorithm to provide adaptive suggestions for the individual learner.
The remainder of the study is structured as follows. The related educational technologies are briefly introduced in Chapter 2. In Chapter 3, we present the main contributions of this thesis: different educational technologies that may be used in a problem-solving learning activity and in computer science education. In Chapter 4, we use the statistical analysis method to investigate the effect of personal traits on the use of MOOCs. In Chapter 5, the data mining technique is used to predict learning behavior in order to provide adaptive learning recommendations. Chapter 6 draws conclusions and discusses future studies.
1.1 Motivation
The new educational technology is broadly applied in courses, programs, and other learning activities. However, not all popular learning materials are suitable for all learners. Each learner has a different attitude toward different forms of instruction.
Therefore, it is necessary to understand learners’ behavior and how to engage them in learning in order to develop educational technology. The term “reciprocal determinism”
means that a person’s behavior is determined by the individual, by the environment, and by their behavior. In the education field, learners have different responses to instructional practices and unique attitudes toward learning. This study is concerned with how to estimate a learner’s response and provide a personalized context for learning. Therefore, the primary goal of the study is to enable a personalized, convenient, and intelligent learning environment. To facilitate a personalized learning environment, we assess the effects of different materials (e.g., static materials and animated games) on learners’ behavior based on reciprocal determinism (see Figure 1-2).
Figure 1-2 The behavior analysis of this study
To make possible a convenient learning environment, this study develops animated gamified material and static material for use in problem-solving activities and computer education. We designed a problem-solving learning system (PSLS) and a computer science learning system (CSLS). The term “gamification” means applying game elements and game design concepts to a nongame context, with the aim of the learner reviewing the learning content via a gamified task. To enable an intelligent learning environment, we use data mining to estimate learning behaviors in online learning environments and to explore adaptive features for personalized learning.
1.2 Contribution
We contribute to the evolution of educational technology by developing various learning systems and providing adaptive learning suggestions for students. We also discuss how tools, behavior, and data analysis contribute to educational technology:
(1)Tools: These are the different materials that influence learner performance and perception. We demonstrate that gender differences exist: game-based material is more useful for males, and static-text material is more useful for females. Intuitive students perform better when using gamified material. Male students who use gamified material perceive solving a problem as easier in gameplay. Thus, a gamified learning system can enhance students’ learning achievement and acceptance of technology as well as reduce cognitive load.
(2)Behavior: We investigate learners’ experience using cloud educational technologies and a learning approach that can assist with this. The results show that the active and global learning style may influence the use of MOOCs and that visual learners are more likely to use gamification instructions.
(3)Analysis: This is the classification algorithm for personalizing learning to engage learners in learning and to enhance their learning motivation and performance.
Figure 1-3 The contributions of this study