Figure 2 - available via license: Creative Commons Attribution 3.0 Unported
Content may be subject to copyright.
Source publication
Data mining in the field of education plays a vital role. The main objective of this analysis is to understand how researchers have done data mining in the past and the current data mining developments in educational research. It describes how academic data and learning analytics applied to academic data. EDM uses computational methods to evaluate...
Citations
... There are also several review studies that indirectly focus on limited aspects of ML for educational data in a given timeline. Alonso-Fernández et al. (2019) have investigated game learning analytics using literature review; Bachhal et al. (2021) have discussed the most important studies conducted until 2021 in educational data mining in general; Yunita et al. (2021) has reviewed the relevant literature on big data in education; Khan and Ghosh (2021) have examined the educational data mining publications from the perspective of student performance analysis and prediction in classroom learning; Salloum et al. (2020) have analysed the literature to find out how data mining was handled by researchers in the past and the most recent trends on data mining in educational research between 2016 and 2019; Albreiki et al. (2021) have reviewed the literature on student' performance prediction using ML techniques where they focused identifying student dropouts and students at risk in literature between 2009 and 2021; Du et al. (2020) have examined 33 publications between 2007 and the first quarter of 2019 to analyse educational data mining research trends where they analysed research topics, methods and sample; Khalaf et al. (2021) have anlaysed the literature on using only supervised ML in the period of 2010-2020; Peña-Ayala (2014) has reviewed the literature on educational data mining between 2010 and first quarter of 2013. ...
... In terms of the fragmentation, the majority of review studies in this area adopt a temporal scope, focusing on specific timeframes. For instance, Alonso-Fernández et al. (2019) explored game learning analytics, Bachhal et al. (2021) covered studies up to 2021, and Salloum et al. (2020) analyzed trends between 2016 and 2019. These fragmented timelines create a gap in understanding the evolution and continuity of ML applications in educational data over an extended period. ...
Integrating machine learning (ML) methods in educational research has the potential to greatly impact upon research, teaching, learning and assessment by enabling personalised learning, adaptive assessment and providing insights into student performance, progress and learning patterns. To reveal more about this notion, we investigated ML approaches used for educational data analysis in the last decade and provided recommendations for further research. Using a systematic literature review (SLR), we examined 77 publications from two large and high-impact databases for educational research using bibliometric mapping and evaluative review analysis. Our results suggest that the top five most frequently used keywords were similar in both databases. The majority of the publications (88%) utilised supervised ML approaches for predicting students’ performances and finding learning patterns. These methods include decision trees, support vector machines, random forests, and logistic regression. Semi-supervised learning methods were less frequently used, but also demonstrated promising results in predicting students’ performance. Finally, we discuss the implications of these results for statisticians, researchers, and policymakers in education.
... Similarly, Schildkamp et al [9]. investigated variables that support and obstruct data-driven decision making in schools, School Effectiveness and School Improvement [16][17][18][19][20]. Their results indicated that a data management system which assists in decision making is useful for minimization of errors in operations and enhancing efficiency and effectiveness of the school [20-23]. ...
In recent years, the use of education data has increased attention. They are important in education planning and development in general. This study assessed the prospects of effective management of educational data in Mbarali District. Our study employed a Cross sectional research design. A quantitative research methodology was used. The population of the study included data managers in primary schools. The study's sample included data managers 285 in primary schools from Mbarali district. Questionnaires were used to gather data. Multiple regression analyses were used to analyse the data. The study revealed that all the four independent variables (effective decision making, minimization of errors, cost effectiveness and efficient operations) uniquely, significantly and positively were influenced by effective data management model (β=0.257 P=0.00), (β=0.301 P=0.00), (β=-0.632 P=0.00) and (β=-0.614 P=0.00) respectively. Therefore, an effective data management support efficiency in decision-making, leads to cost-effective, minimize errors, and support operational effectiveness. Generally the appropriate investment in education is largely determines the success of the implementation of any education policy in a country. The government of Tanzania has given primary school heads power as a primary source of education data in order to ensure that the data submitted to various education authorities are accurate, dependable, and secured. Computers and data storage facilities should be among the data management tools and systems that should be available in schools. Our study then recommends that the government through the Ministry of Education, Science and Technology should make sure current technology is used to manage data in education institutions through updating data management systems and data management tools such as computers, hard drives and data storage facilities to ensure data security and reliability.
... It reflects the merging of numerous sciences, including machine learning, information theory, as well as database systems, as an interdisciplinary research subject. Association rule mining, classification, clustering, regression, as well as outlier detection are some of the most typical data mining activities [16]. b) Frequent pattern mining Such patterns are pruned by frequent pattern mining tools, which consider them to be unwanted or of little interest. ...
span lang="EN-US">The efficient finding of common patterns: a group of items that appear frequently in a dataset is a critical task in data mining, especially in transaction datasets. The goal of this paper is to look into the efficiency of various algorithms for frequent pattern mining in terms of computing time and memory consumption, as well as the problem of how to apply the algorithms to different datasets. In this paper, the algorithms investigated for mining the frequent patterns are; Pre-post, Pre-post+, FIN, H-mine, R-Elim, and estDec+ algorithms. These algorithms have been implemented and tested on four real-life datasets that are: The retail dataset, the Accidents dataset, the Chess dataset, and the Mushrooms dataset. From the results, it has been observed that, for the Retail dataset, estDec+ algorithm is the fastest among all algorithms in terms of run time as well as consumes less memory for its execution. Pre-post+ algorithm performs better than all other algorithms in terms of run time and maximum memory for the Mushrooms dataset. Pre-Post outperforms other algorithms in terms of performance. And for Accident datasets, in terms of execution time and memory consumption, the FIN method outperforms other algorithms.</span
... Machine learning algorithms are widely used in learning analytics (LA) and educational data mining (EDM) [1]. EDM is considered as a methodology for mining regularities from big educational data that are gathered in educational environments [2]. LA is aimed at tools development for analyzing and optimization learning [3,4]. ...
The perspectives of application of machine learning, especially, decision trees, random forest and deep learning for educational data mining problem solving, and learning analytics tools development are considered in the paper. The abilities of sentiment analysis with BERT deep model, clustering based on kMeans with the different approaches to the text vectorization are investigated for the development of learning analytics tools on the example of the learning analytics of some programming MOOCs from Udemy. We analyze 300 titles of MOOCs and proposed their clustering for better understanding the directions of learning and skills, and 1150 sentences that contain the word «teacher» or its synonyms and 2365 sentences about the course for sentiments detection of students and top of words that describe opinions with positive and negative polarities and the issues during learning.
With the spread of online distance learning and digital teaching materials, research analyzing the learning logs from learning management systems and uncovering knowledge that can be used to improve classes is becoming increasingly important. The interquartile method and the interquartile range were applied to the classification of learning patterns, the creation of cluster heat maps, and to outlier detection to improve the robustness of this research. Comparison of extraction methods also clarified that multiple methods were necessary to extract outliers. The analysis results of learning log classification, cluster heat mapping, and outlier detection can also be used to explain the basis of insufficient student effort when teachers make academic interventions. The experimental data showed that learners in need of academic intervention can be categorized by visualizing class engagement with a cluster heat map and outlier extraction.
This research examined student satisfaction and perceived effectiveness of two online learning platforms, Moodle and Google Classroom, among students at the Faculty of Education Sciences in Rabat. A total of 215 students participated in an online survey to evaluate their satisfaction and perception of the platforms' effectiveness as learning management systems. The findings revealed that Moodle received a higher average rating than Google Classroom, with a majority of students considering it more effective for distance learning. However, Google Classroom was favored for its ease of use and fewer technical issues. These insights can assist educators and administrators in understanding student preferences and enhancing the online learning experience.
In the current learning management system, it is difficult for even experienced teachers to grasp the learning situation and to engage in a timely manner for each individual, and the response to this problem remains inadequate. In this study, in order to improve the learner’s engagement and the teacher’s help with the lesson, a cluster heat map of student engagement, teaching material browsing sync ratio, and experimental results of outlier detection were examined. Sync ratios for browsing teaching materials were generated on-site in real time, and teachers could refer to them when teaching lessons. From the analysis of the descriptive statistics in the learning log, the material clickstreams, the quiz scores, and Mahalanobis’ generalized distance were obtained and the engagement cluster heat map was generated based on the weekly learning pattern. As a result, it became possible to clearly discuss the relationship between the appearance frequency of learning patterns and the appearance frequency of abnormal values in teaching material clickstreams and quiz scores. It was clarified that some of the frequency of the appearance of the learning pattern correlated with the frequency of the occurrence of abnormal values of the teaching material clickstream and the quiz score. The results of this study help to find learners who repeat inappropriate learning patterns early and to support appropriate teacher interventions.KeywordsLearning analyticsCluster heat mapSync ratioPrerequisite knowledgeOutlier detectionCorrelation analysisAcademic involvement
