A novel adaptive e-learning model based on Big Data by using competence-based knowledge and social learner activities

Research on Online Education Resources Recommendation Based on Deep Learning

For the problem of knowledge overload in the process of online learning and the traditional algorithm’s poor recommendation accuracy and real-time performance in the massive educational resources, a deep learning-based recommendation model for online educational resources is proposed. First, attribute features of learners and learning resources are extracted, and then text features of learning resources are extracted, and attention fusion of features at multiple different scales is performed using a multiscale fusion strategy. Finally, the fused features are used as input to the multilayer perceptron to train the classification model. Through testing a variety of educational resources, it is verified that the model in this paper has better real-time performance while maintaining high detection accuracy and outperforms the mainstream comparison model in several indexes, which have a certain application value. It provides a new way of thinking for educational platforms to build real-time educational resource recommendations.

Automated Transformation from Competency List to Tree: Way to Competency-Based Adaptive Knowledge E-Evaluation

E-learning is rapidly gaining its application. While actively adapting student-oriented learning with the competency evaluation model, the standard of competency support in existing e-learning systems is not implemented and varies. This complicated integration of different e-learning systems or transfer from one system to another might be challenging if the student had his or her competency portfolio in list form, while another system supports tree-based competency portfolios. Therefore, in this paper, we propose a transformation model dedicated to converting the competency list to a competency tree. This solution incorporates text processing and analysis, competency ranking based on Bloom’s taxonomy, and competency topic area clustering. The case analysis illustrates the model’s capability to generate a qualitative tree from the competency list, where the average accuracy of competency assignment to appropriate parent competency is 72%, but, in some cases, it reaches just 50%.

Challenges and Possibilities of ICT-Mediated Assessment in Virtual Teaching and Learning Processes

The transformations in educational environments due to the immersion of information and communication technologies (ICT) make it necessary to analyze the limits and possibilities of the assessment of the virtual training process. This paper presents an analysis of the meanings of ICT-mediated assessment, establishing what kinds of knowledge are suitable for this type of evaluation, and the challenges and possibilities of virtual tools. For this, we present a systematic review of ICT-mediated evaluation and assessment according to the educational paradigms and their implementation. We highlight that contemporary pedagogical models and their implementation in ICT mediation tools show a trend towards quantitative and summative valuation. The commonly used learning management systems (LMS) include several types of questions oriented to quantitative evaluation, with multiple-choice being the most common. However, new technological approaches like gamification, virtual reality and mobile learning open new assessment possibilities. The ICT educational platforms and new technologies demand new skills for all educational actors, such as digital literacy.

Hierarchy-Based Competency Structure and Its Application in E-Evaluation

The development of information technologies changes the learning process. The amount of publicly available data of e-learning systems allows personalized studies. Therefore, the tutor sometimes is needed for the student’s evaluation and consultation only. To ensure clear evaluation requirements and objective evaluation process, the learning material, as well as the evaluation system, must be discrete and semantically expressed. The list of mastered competencies and skills is more important to the enterprise; therefore, during the last years, the study process has concentrated on competency evaluation too. However, the current practice, when students’ competencies are summarized and expressed as one quantitative metric (score), do not express the list of students’ competencies and their level. To solve the problem, in this paper, we proposed a method for the design of competencies’ tree. The competency tree has to be formatted based on context modeling principles and analysis of Scope-Commonality-Variability. The usage of competency tree for students’ competencies’ evaluation proposes clearly defined and semantically expressed evaluation method for both human and e-learning evaluation process. This paper presents the results of the empirical experiment to adapt the proposed competency tree design and application for competencies’ e-evaluation method, based on flexibility, adaptability, and granularity of learning material.