Educational Data Mining Research Articles

The Role of Artificial Intelligence in the Education of Students with Special Needs

Artificial intelligence (AI) based education represents a significant transformation in the field of education of our age. Artificial intelligence (AI) technology has great potential to enrich the learning experience of special needs students, provide support to teachers, and reduce inequalities in education. Artificial intelligence (AI) technologies can be used to more effectively understand the learning needs of special needs students and provide customized learning experiences for them. Expert systems, adaptive tutorial systems, dialogue-based systems, learning analytics and educational data mining are widely used AI systems developed to increase productivity in educational environments, facilitate achievement of learning goals, provide instant feedback and enrich student interaction. Assessing the learning inclinations, strengths, and weaknesses of students with special needs enables AI to provide tailored learning content and resources that cater to their individual requirements effectively. In this article, tried to present a road map to teachers and researchers by examining the role of AI-based technologies in the education of special needs students, the AI-based technologies that can be used, and the issues to be considered when choosing these technologies.

Educational Data Mining: A Foundational Overview

Educational data mining (EDM) is a novel scientific area that focuses on developing and applying methods to analyze datasets generated within educational settings. This paper outlines the evolution, significance, and applications of EDM. With the increasing popularity of e-learning in web-based educational systems, EDM has expanded to include a variety of analytical methods and data sources. Some key methodologies addressed include classification, regression analysis, clustering techniques, association rule mining, and Natural Language Processing, among others. Additionally, this paper looks at how EDM can facilitate data-driven decision-making among other areas such as curriculum development and customization of learners’ experiences. It also touches on issues related to the challenges of the scientific field. Finally, some projections about EDM’s future trends are made, especially concerning its integration into AI technologies and development trends like augmented reality or virtual reality, which imply greater possibilities for changes than any other series witnessed before within this sphere.

Enhancing Education and Teaching Management Through Data Mining and Support Vector Machine Algorithm

This study investigates the effectiveness of the SVM+TLBO approach for predicting student performance and evaluating learning abilities in educational settings. By integrating Support Vector Machines (SVM) with Teaching-Learning-Based Optimization (TLBO), the research aims to enhance predictive accuracy and efficiency compared to traditional methods, including Decision Trees, Ant Colony Algorithms, Clustering Algorithms, Convolutional Neural Networks (CNN), Neural Networks, Support Vector Machine (SVM) without Optimization. Results indicate that the SVM+TLBO model significantly outperforms these methods, providing robust predictions and valuable insights into student learning patterns. The findings underscore the importance of data-informed decision-making in education, enabling educators to identify at-risk students and tailor instructional strategies effectively. This research contributes to the growing field of educational data mining, highlighting the potential of advanced machine learning techniques to optimize educational outcomes and foster personalized learning experiences.

Students' performance prediction employing Decision Tree

An optimized educational community is a must in this modern era. The intersection of educational activities and the transformative potentials of Educational Data Mining (EDM) should be traversed, highlighting the reasoning behind the importance of EDM. Prior prediction of how a student stands academically, can facilitate them towards a much safer approach with their life decisions. This study uses the vast power and analytical domain of EDM, combining it with machine learning models, upholding an accurate prediction of students' academic performance. The study consists of a dataset containing academic, demographic and social data of undergraduate students. The paper aims to analyze comprehensively the features that act behind academic performance. Lastly, it compares the impact of non-academic data separately on a student's performance and with academic data as well. Traditional machine learning algorithms perform quite well in general, with SVM giving a best accuracy of around 95% with academic data, while training and testing the model without academic data still gives a good performance of 93%. The hierarchical tree from Decision Tree visualizes the key features, which include past results, family members' qualification levels and their jobs, hobbies of the student, commute time, and more.

An Analysis of Student Satisfaction and its Relationship with Academic and Social Factors in University Dropout

Over the last 50 years, Higher Education has experienced significant development, which has been associated with challenges that have yet to be solved. In this sense, university dropout is a global phenomenon that worries universities all over the world. Many research studies describe the possible causes of this phenomenon, but the most interesting are those that, due to their predictive potential, have the possibility of preventing it. The aim of this article is to study how important students perceive the different reasons for dropout in relation to the idea of abandoning the degree. For this purpose, the Spanish version of the Questionnaire of Motives for Higher Education Dropout (QMA_es; Almeida et al., 2019) was applied to a sample of 927 first- and second-year university students. These data have been processed using educational data mining (EDM) techniques, obtaining a decision tree that correctly classifies the sample in 81.1%. The results show that variables related to student satisfaction (satisfaction with academic choice, satisfaction with performance, and satisfaction with the financial situation) and to the academic and social environments play a predominant role in the approach to dropout, above other institutional, financial, and wellbeing variables.

Exploiting the Regularized Greedy Forest Algorithm Through Active Learning for Predicting Student Grades: A Case Study

Student performance prediction is a critical research challenge in the field of educational data mining. To address this issue, various machine learning methods have been employed with significant success, including instance-based algorithms, decision trees, neural networks, and ensemble methods, among others. In this study, we introduce an innovative approach that leverages the Regularized Greedy Forest (RGF) algorithm within an active learning framework to enhance student performance prediction. Active learning is a powerful paradigm that utilizes both labeled and unlabeled data, while RGF serves as an effective decision forest learning algorithm acting as the base learner. This synergy aims to improve the predictive performance of the model while minimizing the labeling effort, making the approach both efficient and scalable. Moreover, applying the active learning framework for predicting student performance focuses on the early and accurate identification of students at risk of failure. This enables targeted interventions and personalized learning strategies to support low-performing students and improve their outcomes. The experimental results demonstrate the potential of our proposed approach as it outperforms well-established supervised methods using a limited pool of labeled examples, achieving an accuracy of 81.60%.

Predictive Modeling for Enhancing MOOC Completion Rates: A Case Study

In the realm of online asynchronous learning platforms, accurately tracking student performance to predictcourse completion times poses a significant challenge. Completion rates for MOOCs are typically low, with abias towards participants with higher education levels. Understanding factors such as student motivation,engagement, participation, and learning pathway design is crucial for improving student outcomes in onlinecourses. This research developed a predictive framework utilizing advanced deep learning techniques toaccurately forecast course completion times for participants enrolled in an introductory programming course("Python for Beginners" course on the Open Learning Platform of University of Moratuwa Sri Lanka). Byaccurately tracking student performance and leveraging a diverse dataset encompassing demographic andeducational variables, the research seeks to identify factors influencing course completion and predictindividual student outcomes. By utilising deep learning techniques, the prediction performance of the modelwill be improved, ultimately contributing to a more precise forecast of course completion times forparticipants. Evaluation of the model resulted in low Mean Absolute Error (MAE) of 0.0080 and low MeanSquared Error (MSE) of 0.0033 which promises the effectiveness of the developed method in accuratelypredicting course completion times for students. The findings of this study may help increase the successfulcompletion rate of such courses which are delivered in the online asynchronous mode. The study employedadvanced deep learning models optimized through Bayesian methods, highlighting the potential of thesetechniques to enhance MOOC completion rates by offering precise forecasts and actionable insights intostudent engagement. The comprehensive analysis revealed that variables such as 'Current_Lesson', 'SessionTime Category', and 'District_Score' significantly influence completion times. The robust methodologicalframework, including feature engineering, model training, and hyperparameter optimization, sets a precedentfor future research in the field. This research contributes to educational data mining and predictive analytics,offering a scalable approach to improving completion rates and educational outcomes across various onlinelearning platforms. Future research should explore incorporating real-time data and longitudinal studies toenhance model accuracy and generalizability. Additionally, addressing potential biases in the dataset, such asdemographic, prior knowledge, and resource access disparities, is essential to ensure the fair and equitableapplication of the model across diverse student populations. Expanding the research to include a wider rangeof courses and institutions will further validate the model's robustness and applicability in differenteducational contexts.

Predicting Student Performance Using Educational Data Mining: A Review

Educational Data Mining (EDM) strategies facilitate the efficient and in-depth analysis of student data. EDM provides useful insights into comprehending student learning patterns and identifying factors that influence academic success. This review aims to evaluate the efficacy of classification algorithms popularly explored in EDM for predicting student performance and identifying common trends in existing EDM research. The review follows a systematic approach, relevant research articles have been cited following an inclusion and exclusion criteria to ensure the selection of studies that specifically address the use of EDM techniques for predicting student academic achievement. According to the review findings, most researchers have utilized the features of cumulative grade point average, internal and external assessment, and demographic information to predict student performance. The most common techniques in EDM for predicting students’ performance are Naïve Bayes and Decision Trees. The review also focuses on the potential for bias, key examination of challenges, and possible future directions in the field. In the context of student performance prediction, ethical considerations regarding privacy, data handling, and the interpretation of results are also identified

Retraction Note: Towards developing hybrid educational data mining model (HEDM) for efficient and accurate student performance evaluation

Retraction Note: Towards developing hybrid educational data mining model (HEDM) for efficient and accurate student performance evaluation

WEKA: A Tool for Shaping Effective Student Learning Strategies for College School Leavers

As college school leavers transition into higher education or the workforce, they face numerous challenges in adapting to new learning environments and expectations. Effective learning strategies are crucial to ensuring their success in these new settings. This paper explores how WEKA, a powerful data mining tool, can be leveraged to shape and enhance student learning strategies for college school leavers. By analysing educational data, WEKA can provide insights into the most effective learning methods, helping educators tailor their approaches to meet the specific needs of these students. The paper discusses the application of WEKA in educational data mining, highlights its capabilities, and presents case studies demonstrating its effectiveness in shaping learning strategies.

An In-Depth Evaluation of Educational Burst Games in Relation to Learner Proficiency

Game-based learning assessments rely on educational data mining approaches such as stealth assessments and quasi mixed methods that help gather data on student learning proficiency. Rarely do we see approaches where student proficiency in learning is woven into the game’s design. Educational burst games (EBGs) represent a new approach to improving learning proficiency by designing fast-paced, short, repetitive, and skill-based games. They have the potential to be effective learning interventions both during instruction in the classroom and during after-school activities such as assignments and homework. Over five years, we have developed two EBGs aimed at improving linear algebra concepts among undergraduate students. In this study, we provide the results of an in-depth evaluation of the two EBGs developed with 45 participants that represent our target population. We discuss the role of EBGs and their design constructs, such as pace and repetition, the effect of the format (2D vs. 3D), the complexity of the levels, and the influence of prior knowledge on the learning outcomes.

Predictive Analysis of Students’ Learning Performance Using Machine Learning

Several researchers and educational institutions got attracted to the domain of predicting the performance of the students to classify the educational level of student performance. Though the educational sector uses several techniques for extracting useful information about them and the measures to be undertaken in the learning process, it is necessary to develop a student performance assessment model to assist the students as well as faculty members to improve their performance to the next level. This research work majorly concentrates to examine and identify useful rules and patterns to motivate the students for handling their education as well as career in a better way and also to improve the functioning of academics to supervise the policies for students’ benefit. Here, EDM is employed to identify the effective data which helps in applying the active learning in technical applications. Initially, a review of different DM, machine learning (ML), and meta-heuristic models to assess the performance of the students. the proposed models can be employed as an appropriate tool for mining educational data to achieve effective performance assessment of the students.

A BIBLIOMETRIC ANALYSIS OF RESEARCH ON DROPOUT IN OPEN AND DISTANCE LEARNING

The purpose of this study is to examine research on school dropout in open and distance education in the Web of Science (WoS) database using bibliometric analysis and to reveal trends in this area. In line with this goal, a total of 1,615 studies published between 1980 and 2022 were identified in the Web of Science (WoS) indexes. Descriptive and evaluative bibliometric methods were employed in the analysis of these publications, and the results were visualized using VOSviewer software. According to the research findings, studies on school dropout in open and distance education intensified in 2019. The analysis revealed that E.T. Pascarella is the most cited author, and F.D. Pereira has the highest co-authorship network. An examination based on institutions showed that the Universitat Autònoma de Barcelona has the highest number of publications, while the University of Michigan ranks first in terms of citation numbers. Furthermore, in terms of publication productivity and citation numbers, the United States is ranked first, followed by Spain. Looking at the keywords used in articles on the topic, early studies emphasized concepts such as “distance education”, “student retention”, “attrition”, “student success”, “social integration”, “academic integration”, “survival analysis”, “education policy”, “graduation”, and “financial aids”. In subsequent years, these were replaced by terms such as “learning analytics”, “educational data mining”, “systematic review”, “engagement”, “drop prediction”, “decision tree”, “student performance”, “gamification”, “massive open online course- MOOC”, and “artificial intelligence”. In this context, discussions were conducted within the framework of the literature, and various recommendations were provided based on the obtained findings.

A Student Education Data Mining Method based on Student Sequential Behaviors and Hybrid Recurrent Neural Network

This research aims to propose a student education data mining method based on a hybrid recurrent neural network and improved support vector machine-decision tree algorithm through in-depth analysis of student behavior sequences. The method combines the feature extraction capability of a hybrid recurrent neural network and the nonlinear mining efficiency of support vector machine-decision tree algorithm to achieve efficient prediction of students’ learning behavior and performance. Experimental results have shown that the designed method completed an APA of 91.3% and 89.2% for the HR-SDT model on the Student_1 and Student_2 datasets, respectively. The F1 score average values of the HR-SDT model reached 86.7% and 81.9%, respectively. The results indicate that the student behavior data mining method based on hybrid recurrent neural networks can accurately predict the learning behavior and performance of students, providing valuable insights and decision support for educators.

DETERMINING STUDENT'S ONLINE ACADEMIC PERFORMANCE USING MACHINE LEARNING TECHNIQUES

Predicting student's academic performance during online learning has been considered a major task during the pandemic period. During the online mode of learning, academic activities have been affected in such a way that the management of educational institutions has planned to design support systems for predicting the student's performance to reduce the dropout ratio of the students and bring improvement in academic activities. During COVID-19, the main challenge is maintaining student's grades by predicting their academic performance using different techniques such as Education Data Mining and Learning Analytics. Different features have been identified related to the teaching mechanisms in online learning, which have a great impact on the improvement of academic performance. A high-quality dataset helps us to generate productive results, which in turn helps us to make effective decisions for promoting high-quality education. In this research, five prediction models for predicting academic performance have been proposed by collecting an imbalanced dataset of 350 students from the same computer science domain. After applying pre-processing techniques for cleaning the data, machine learning models have been applied, including K-Nearest Neighbor Classifier, Decision Tree, Random Forest, Support Vector Classifier, and Gaussian Naive Bayes. Results have been predicted for an imbalanced and balanced dataset after feature selection. Support Vector classifier has produced the best results in a balanced dataset with selected features by giving an accuracy of 96.89%.

Data-driven decision making in higher education to ensure quality education: a bibliometric review study

In the evolving landscape of higher education, data-driven decision-making has emerged as a crucial strategy for enhancing quality education. This bibliometric review study examines the existing literature on data-driven decision-making within higher education to outline its impact on the quality of education. This study employs a thorough bibliometric analysis to gather and analyze scholarly articles from major databases. It identifies main trends, influential authors, and key research themes in the field. The findings reveal that there is increasing focus on leveraging data analytics, learning analytics, and educational data mining to inform policy, teaching methods, and administrative strategies. The study also highlights the challenges and opportunities associated with implementing data-driven approaches, such as data privacy concerns and the need for robust data governance frameworks. By synthesizing current research, this review provides a holistic understanding of how data-driven decision-making can be strategically employed to ensure and enhance the quality of education in higher institutions. This paper not only contributes to the academic discourse by mapping the intellectual landscape but also offers practical insights for educators, policymakers, and administrators aiming to foster a data-informed educational environment. Keywords: data-driven decision, university, higher education, quality assurance, quality education, university management, bibliometric analysis.

Sustainability of Quality Management by Implementing Data Mining to Predict Academic Achievement

This research aims to predict the academic achievement of Pamulang University students using Educational Data Mining (EDM) techniques. With the increasing number of students and the complexity of academic data, it is important to apply methods that can analyze and predict learning outcomes to improve learning strategies and academic support. This study collected data from various sources, including course grades, attendance, and participation in extracurricular activities. The collected data is then analyzed using EDM techniques such as decision trees, neural networks, and support vector machines to identify patterns and factors that contribute to student academic achievement. The results of the analysis show that factors such as attendance, involvement in campus activities, and previous test scores have a significant influence on academic achievement. This research provides valuable insights for the development of targeted interventions, with the aim of improving academic outcomes and facilitating more effective learning strategies at Pamulang University. These findings also offer contributions to further research in the field of EDM and its application in higher education contexts.

EVALUATING THE IMPACT OF LEARNING ACTIVITIES ON QUIZ SUBMISSION IN LEARNING MANAGEMENT SYSTEM (LMS)

With the rise of educational technology, the trend of online learning is gradually becoming popular. Quiz submissions are a crucial assessment activity on Learning Man- agement Systems (LMS). This study investigates the factors influencing student quiz sub- missions in online learning environments. An Apriori Algorithm-Based Association Rule Analysis to assess the impact of various learning activities on student quiz submissions has been used in this article with actual online learning datasets. Our data mining results reveal that announcements and conferences have a significant positive influence on quiz submis- sions. In contrast, activities like page lectures, discussions, and reflective assignments may not substantially impact student submission behavior. The results of this research can be used to recommend teachers to organize appropriate learning activities on LMS to promote students’ quiz submission. Keywords: Data Mining in Education; Online Learning Activities; Online Assign- ment Submission

Uncovering student profiles. An explainable cluster analysis approach to PISA 2022

Educational data mining (EDM) applied to the wealth of data generated from international large-scale assessments (ILSAs) shows potential for identifying successful educational initiatives. Despite limited research on clustering methods in ILSAs, leveraging these methods to uncover student profiles can help decision-making in designing tailored programs. This study aims to identify and characterize 15-year-old student profiles using PISA 2022 data and reveal insights into the relationship between these profiles and factors such as ICT availability and use, gender, academic performance, and educational expectations. We analyzed PISA 2022 Spanish student data (n = 30,800) with a selection of 74 contextual variables, applying an end-to-end explainable cluster analysis methodology that integrates different machine learning (ML) and explainable artificial intelligence (XAI) techniques. This methodology covered data pre-processing, dimensionality reduction, clustering, and classification to ensure data quality and result explainability. We obtained 16 derived variables, 7 student clusters, and an optimal XGBoost classifier with a global accuracy of 0.8643. Using local and global SHAP values, we interpreted clusters, finding that socio-economic status and ICT availability and use at home are the most important factors differentiating student profiles. Our findings suggest the need to emphasize (i) proper ICT accessibility and use, as well as student support networks to improve academic performance, (ii) gender-specific well-being programs, and (iii) the encouragement of educational expectations tailored to students’ gender and their exposure to higher education. These results pave the way for personalized academic policies and programs through ML-based tools for uncovering student profiles.

An Extended Learning Analytics Framework Integrating Machine Learning and Pedagogical Approaches for Student Performance Prediction and Intervention

AbstractThe use of educational data mining and machine learning to analyse large data sets collected by educational institutions has the potential to discover valuable insights for decision-making. One such area that has gained attention is to predict student performance by analysing large educational data sets. In the relevant literature, many studies have focused on developing prediction models on student performance but comparatively less work exists on actions taken based on predicted at-risk students and evaluating their impact. Learning Analytics Intervention (LAI) studies have emerged as an approach that aims to address this gap. In LAI studies, student risk levels are predicted and disseminated to relevant stakeholders (academics, administrators and students) using learning analytics (LA) tools for targeted interventions. The interventions themselves are mainly left under the discretion of the academics and/or administrators, who are aware of the learning context and have the authority to make decisions, with LA tools facilitating this process. LAI studies have shown success in improving outcomes (e.g. improve pass rates, retention, grades), but their uptake has been slow. The main impediment to piloting LAIs by academics has been the lack of access to LAI infrastructure, which requires institutional investments to develop predictive models collecting data from diverse IT systems. Another challenge in LAIs is the development of effective interventions. This paper presents an extended LAI framework, termed Student Performance Prediction and Action (SPPA), which provides access to LAI infrastructure for academics to pilot LAIs in their courses without the need for institution-wide efforts. SPPA and its features are seamlessly accessed via a web browser and academics can develop course-specific predictive models based on historical course assessment data. Furthermore, SPPA integrates sound pedagogical approaches and provides relevant information (such as students’ knowledge gaps, personalised study plans) to assist academics in providing effective interventions. SPPA was evaluated by a number of academics piloting LAIs in their courses. Quantitative and qualitative data was collected and analysed. Academics were able to provide effective interventions using SPPA and also had a positive outlook on using SPPA and its features. SPPA is also provided as an open-source project for further development and can be a catalyst for widescale uptake in LAIs. Furthermore, a model for continuous improvement in LAIs is outlined along with a number of areas for future research and development.