Purpose: This systematic literature review aims to identify the pattern of data mining (DM) research by looking at the levels and aspects of education. Design/methodology/approach: This paper reviews 113 conference and research papers from well-known publishers of educational data mining (EDM) and learning analytics-related research using a recognized literature review in computer science by Carrera-Rivera et al. (2022a). Two major stages, planning and conducting the review, were used. The databases of Elsevier, Springer, IEEE, SAI, Hindawi, MDPI, Wiley, Emerald and Sage were searched to retrieve EDM papers from the period 2017 to 2023. The papers retrieved were then filtered based on the application of DM to the three educational levels – basic, pre-tertiary and tertiary education. Findings: EDM is concentrated on higher education. Basic education is not given the needed attention in EDM. This does not enhance inclusivity and equity. Learner performance is given much attention. Resource availability and teaching and learning are not given the needed attention. Research limitations/implications: This review is limited to only EDM. Literature from the year 2017 to 2023 is covered. Other aspects of DM and other relevant literature published in EDM outside the research period are not considered. Practical implications: As the current trend of EDM shows an increase in zeal, future research in EDM should concentrate on the lower levels of education to identify the challenges of basic education which serves as the core of education. This will enable addressing the challenges of education at an early stage and facilitate getting a quality education at all levels of education. Appropriate EDM techniques for mining the data at this level should be the focus of the research. Specifically, techniques that can cater for the variation in learner abilities and the appropriate identification of learner needs should be considered. Social implications: Content sequencing is necessary in facilitating an easy understanding of concepts. Curriculum design from basic to higher education dwells much on this. Identifying the challenge of learning at the early stages will facilitate efficient learning. At the basic level of learning, data on learning should be collected by educational institutions just as it is done at the tertiary level. This will enable EDM to accurately identify the challenges and appropriate solutions to educational problems. Resource availability is a catalyst for effective teaching and learning. The attributes of a learner will enable knowing the true nature of the learner to determine the prospects of the learner. Originality/value: This research has not been published in any journal. The information presented is the original knowledge of the authors. However, a pre-print of the work is in Research Square.
14 August 2018 in International Journal of Computer Applications
The major challenge of most basic schools is inadequate educational resources despite a conscious effort to constantly provide. This is a result of inaccurate data management leading to inappropriate predictions for effective planning. The actual efficiency of a system is determined by its ability to predict real-life data with speed and accuracy. In this work, the neural educational expert system (ES) is evaluated using mathematical models for predicting the availability of resources for the growing school-aged population using a criteria-based formative evaluation to know resource life and its effect on availability. This will help in the decision to add more resources by knowing when and how the resources should be added. Technical mathematical model generation through differential equations is used to fuse the factors affecting the availability of educational resources. The real-life data is used in prediction regarding the actual enrollment of learners and the availability of resources. The model is evaluated and critically analyzed to know the degree of accuracy and the steady state. The findings revealed that the resources decay and attrite at an exponential rate in the long run and the constant number of resources provided cannot cater for the rate of decay, resulting in inadequacy. A proposed algorithm for managing the resources is presented.