Educational Data Mining Research Articles

Character Data Mining in Educational Scene

Teaching and learning have been completely transformed by the quick growth of information technologies like big data, artificial intelligence, and the Internet of Things. Traditional educational methods can no longer satisfy the demands of modern fast-paced and lifelong learning, making the mining of educational data more urgent. Character mining in images is increasingly applied in educational settings. Artificial intelligence and machine learning algorithms, learning behaviors, such as CNN(Convolutional Neural Networks and RNN()Recurrent Neural Networks), have been used, to predict student performance, and provide personalized recommendations for educational resources. Therefore, research on the application of character mining in educational scenes should be conducted and implemented using OCR technology and the CRNN algorithm. The prediction and mining results are promising and hold commercial value. With the diversification of educational scenarios, the adaptability and flexibility of algorithms will become important research directions. Ultimately, the advancement of these technologies will further drive the digital transformation of education, providing learners with richer and more efficient learning resources.

Educational data mining for student performance prediction: feature selection and model evaluation

Student performance is a multidimensional concept that includes academic accomplishment and cognitive development. It measures the performance of educational institutions, teaching methods and individual efforts. Engagement, motivation and support networks have a substantial impact on performance results. In this research, we intend to establish an intelligent data mining-based model for predicting student performance through a novel feature selection approach. We propose an innovative Adaptive Sea Horse Optimization (ASHO) to select the crucial features to predict the education performance level. We gathered a xAPI-Edu-Data dataset which includes students’ numerous academic details, to train our suggested model. The Z-score normalization algorithm is employed to pre-process the obtained raw data, it improves the quality of the data. We utilized Independent Component Analysis (ICA) to extract relevant characteristics from the processed data. We utilize the ASH algorithm for feature selection, it dynamically adjusts search parameters, efficiently exploring the feature space to locate the ideal subset of features for improving the predictive performance. The selected features are classified by the implementation of the eXtreme Gradient Boosting (XGBoost) algorithm for predicting student performance. Our recommended approach is implemented in Python software. The finding evaluation phase examines the suggested model's prediction effectiveness with various parameters such as precision, accuracy, recall and f1 score. We performed a comparison analysis with other traditional methods to determine the effectiveness of the proposed approach. The experimental results demonstrate that the proposed prediction approach performed better than other existing approaches.

Personalizing the learning process through data mining in higher education

Relevance. The rapid evolution of the modern labor market necessitates a shift from traditional, standardized career counseling to personalized educational trajectories that account for individual qualities, skills, and preferences, ensuring better professional adaptability and satisfaction. Purpose. The purpose of the study is to develop and validate a model that will facilitate the selection of a person-centred educational and professional pathway for students. Methodology. The research methods are comparative, qualitative, and statistical analysis, experimental method, modelling, and prototyping. Results. The main result of the study was the creation and successful application of an original learning model integrated with modern analytical approaches, including predictive analysis mechanisms for adapting and optimizing individual educational trajectories, which significantly improved the efficiency of the learning process. Experimental implementation showed that students who used the developed model to create their individual educational trajectories achieved a significant improvement in their academic performance and motivation to learn compared to the control group. The hypothesis that personalized guidance influences the choice of more appropriate curricula and courses was confirmed, which in turn has a positive effect on academic performance and satisfaction with learning. The presence of positive feedback from students and teachers also indicates the high adaptability of the model and its potential for scaling up and further implementation in educational practice. Conclusions. The study validated the positive impact of a personalized approach on students' academic motivation and performance, revealing significant advantages in engagement, strategic career planning, and long-term purposefulness, while also highlighting the need for further research to scale the model, optimize prediction algorithms, and adapt the approach to diverse learning environments and educational standards. Keywords: adaptive education; statistical modelling; educational modelling; learning technologies; educational motivation; forecasting methodologies; qualification development

Bibliometric insights into data mining in education research: A decade in review

This bibliometric study on data mining in education synonymous with big educational data utilizes VOSviewer and Harzing’s Publish and Perish to analyze the metadata of 1,439 journal articles found in Scopus from 2010 to 2022. As bibliometric analyses in this field are lacking, this study aims to provide a comprehensive outlook on the current developments and impact of research in this field. This study employs descriptive and trends analysis, co-authorship analysis, co-citation analysis, co-occurrences of keywords, terms map analysis, and analysis of the impact and performance of publications. It also partially replicates a similar study conducted by Wang et al. (2022), who used the Web of Science (WoS) database. The study is reported in an article entitled ‘Big data and data mining in education: A bibliometrics study from 2010 to 2022’. Results show that data mining in education is a growing research field. There is also a significant difference between the publications in Scopus and WoS. The study found several research areas and topics, such as student academic performance prediction, e-learning, machine learning, and innovative data mining techniques, to be the core basis for collaborating and continuing current research in this field. These results highlight the importance of continuing research on data mining in education, guiding future research in tackling educational challenges.

Advancing Educational Insights: Explainable AI Models for Informed Decision-Making

Abstract: Over the past two decades, the integration of machine learning (ML) techniques within educational frameworks has garnered significant attention. However, despite its widespread adoption, there remains a dearth of research focusing on developing AI systems with a core emphasis on interpretability and explainability. This paper seeks to bridge this gap by proposing an advanced framework that not only predicts students' performance accurately but also offers reliable and interpretable results tailored for career counseling. The framework merges the concepts of ML and Explainable AI (XAI) to address the complexities of career counseling in educational settings. Drawing inspiration from educational data mining, the framework aims to provide insights conducive to students' career growth and decision-making processes. By incorporating MLbased White and Black Box models, the approach analyzes a comprehensive educational dataset comprising academic and employability attributes crucial for job placements and skill development. To enhance interpretability, the framework leverages the NGBoost algorithm, known for its efficiency in prediction modeling. Additionally, it integrates Local Interpretable Modelagnostic Explanations (LIME) and Shapley Additive Explanations (SHAP) methods for providing both local and global explanations of model predictions, ensuring transparency and comprehensibility. Through a series of use cases, the paper showcases the applicability and effectiveness of the framework in providing actionable insights to educators and students alike. In conclusion, this research contributes to the advancement of career counseling in educational contexts by offering a robust and interpretable ML-based framework. By providing transparent insights into students' academic performance and career prospects, the approach facilitates informed decision-making and supports personalized guidance for optimal career trajectories.

A survey on automated student evaluation and analysis using machine learning

The problem of automated student evaluation and analysis is a widespread issue in the education sector, where the manual evaluation of students' performance and progress can be time-consuming, prone to errors, and lacking in efficiency. The current evaluation methods do not provide real-time insights and feedback to students, leading to a lack of engagement and motivation. Many Methodologies have been developed for estimating and analyzing the students' performance. One such methodology developed using: Machine learning, educational data mining, Predicting achievement. This methodology has no concern for the aspects like non-academic activities, personality traits of students and other technical and non-technical skills. The goal of automated student evaluation and analysis is to develop a system that can accurately and efficiently evaluate and analyze students' performance and provide meaningful feedback in real-time. The system should be able to analyze large amounts of data from various sources, exams, and provide detailed insights into the strengths and weaknesses of individual students. The system should also provide teachers with the tools to track student progress over time, identify areas for improvement, and provide personalized feedback to each student. The challenge of creating such a system lies in accurately analyzing and interpreting large amounts of data, identifying patterns and trends, and providing meaningful insights and feedback to students and teachers in real-time. It requires the integration of advanced artificial intelligence and machine learning techniques, as well as user-friendly interfaces and data visualization tools.

Exploring factors influencing academic literacy – A data-driven perspective

Background: Data science and machine learning have shown their usefulness in business and are gaining prevalence in the educational sector. In illustrating the potential of educational data mining (EDM) and learning analytics (LA), this article illustrates how such methods can be applied to the South African higher education institution (HEI) environment to enhance the teaching and learning of academic literacy modules.Objectives: The objective of this study is to determine if data science and machine learning methods can be effectively applied to the context of academic literacy teaching and learning and provide stakeholders with valuable decision support.Method: The method applied in this study is a variation of the knowledge discovery and data mining process specifically adapted for discovery in the educational environment.Results: This study illustrates that utilising educational data can support the educational environment by measuring pedagogical support, examining the learning process, supporting strategic decision-making, and predicting student performance.Conclusion: Educators can improve module offerings and students’ academic acculturation by applying EDM and LA to data collected from academic literacy modules.Contribution: This manuscript contributes to the field of EDM and LA by illustrating that methods from these research fields can be applied to the South African educational context and produce valuable insights using local data, providing practical proof of its feasibility and usefulness. This is aligned with the scope of this journal as it pertains to innovations in information management and competitive intelligence.

Exploring the role of machine learning in forecasting student performance in education: An in-depth review of literature

The literature on the role of machine learning in forecasting student performance in education lacks comprehensive data quality, equitable and interpretable models, consideration of contextual and causal factors, and the integration of human expertise. This review will explore machine learning types, algorithms, predictive performance, and impact on student performance in education. A systematic literature review based on articles published in the past 2019–2023 period Methods: The IEEE Xplore database was searched by using keywords such as "Educational Data Mining," "Student Performance Prediction," "Evaluations of Students," "Performance Analysis of Students," and "Learning Curve Prediction." were employed and 50 papers were selected. Results: The analysis of the results highlighted prominent patterns. Half of the studies favored supervised learning methods, with decision trees leading (19 instances), followed by Long Short-Term Memory and Random Forest (16 each), and K-Nearest Neighbor and Naive Bayes (12 and 11 times). Support Vector Machine and Logistic Regression were noted 10 and 9 times, respectively. Noteworthy were ANN, CNN, and Xgboost. Positive impacts were evident in 36 cases; only one showed negative effects, while 13 indicated intricate relationships. This study helped in understanding the prevalent machine learning methods used for predicting student performance, provides a benchmark for assessing the effectiveness of new or alternative techniques. Conclusion: This review highlights the varied machine learning uses in predicting student performance in education, emphasizing supervised methods, diverse algorithms, and complex intervention impacts.

Exploring Software Infrastructures for Enhanced Learning Environments to Empowering Education

Recently, the education sector has undergone a notable change due to the incorporation of technology, resulting in the emergence of Educational Technology (EdTech). This new trend has completely transformed the learning process for students, teaching methods for educators, and operations of educational institutions. Due to EdTech, education has become simpler to access, engaging, and efficient, providing customized and diverse learning experiences. This article explores into the significant influence of EdTech on the field of education and the promising opportunities it offers for the future. EdTech has become a significant enabler, allowing institutions to meet evolving student needs and cultivate new skillsets without being limited by geographical barriers. EdTech integrates digital and technological media with conventional methods of instruction to enable various forms of learning, offering adaptability, enhancing engagement, and providing high-quality educational solutions. EdTech tools empower educators to track student engagement, encourage interactive and creative learning experiences, and stand for human-centred education focusing on critical thinking, innovation, and entrepreneurial activity. Exploring deeper relationships between educational data as well as predicting how well students do in school has been made possible through educational data mining. Presented is a novel model utilizing machine learning computational methods to forecast the EdTech for the students by using their midterm exam results. Various machine learning algorithms were assessed and providing the EdTech for improving their performance in final exam. This study comprehensively examines different EdTech technologies and recommend a unified model that could serve as a solid framework for classroom teaching.

Evaluation of Academic Self-Efficiency, Community Feeling, and Academic Achievement of Students in the Process of the Covid-19 Pandemic by Data Mining Techniques

Thanks to the advancement of technology, vast amounts of data are being generated in various fields on a daily basis. The research on identifying hidden patterns and extracting useful information from big data has become increasingly important. In the field of education, the availability of large datasets has allowed for the emergence of data mining techniques as an alternative to traditional statistical methods. Unlike traditional statistical methods, data mining can uncover hidden relationships between variables, thus avoiding the loss of valuable information and enabling the utilization of essential data in education. By unlocking valuable insights and predicting important relationships, educational data mining (EDM) has the potential to enhance and improve the quality of education. This study aims to demonstrate the predictive power of EDM through a sample application and draw attention to its implications. The dataset used in this study consists of survey responses collected from university students. The variables in the dataset include academic self-efficacy, sense of community, academic achievement averages, and various demographic variables of distance education students. Descriptive modeling was employed to identify latent patterns between variables, while a predictive model was utilized to estimate variables. In order to achieve this, both association rule mining and classification algorithms were employed. The findings of this study indicate that EDM can effectively identify relationships between variables and make accurate predictions.

A Toolbox for Modelling Engagement with Educational Videos

With the advancement and utility of Artificial Intelligence (AI), personalising education to a global population could be a cornerstone of new educational systems in the future. This work presents the PEEKC dataset and the TrueLearn Python library, which contains a dataset and a series of online learner state models that are essential to facilitate research on learner engagement modelling. TrueLearn family of models was designed following the "open learner" concept, using humanly-intuitive user representations. This family of scalable, online models also help end-users visualise the learner models, which may in the future facilitate user interaction with their models/recommenders. The extensive documentation and coding examples make the library highly accessible to both machine learning developers and educational data mining and learning analytics practitioners. The experiments show the utility of both the dataset and the library with predictive performance significantly exceeding comparative baseline models. The dataset contains a large amount of AI-related educational videos, which are of interest for building and validating AI-specific educational recommenders.

Discover Frequent Patterns from Academic Data Of Student Information System

Numerous researchers have explored the realm of data mining in education. The primary goal is knowledge discovery, aiming to support staff in efficiently managing educational units, refining student activities, and ultimately elevating learning outcomes. In this study, we utilize association rules mining, implementing the Apriori algorithm to extract insights from academic datasets sourced from the student information system of Sebha University, Libya. Genuine data is sourced from the cloud server. The algorithm is then applied to unveil relationships among 11 attributes within students' academic records spanning four years. The resulting patterns undergo experimental evaluation, considering support and confidence values. These specific rules are subsequently categorised into four classes and scrutinised for further validation. The proposed method yields valuable patterns pertaining to students' academic progress and retains crucial insights for predicting decisions regarding course additions and drops.

Teacher Performance Prediction Using Machine Learning

Student performance is one of the crucial and necessary part in the educational system due to its large volumes of real-time data that cannot be analyzed manually by the humans. So, here comes machine learning that is used to easily predict the performance of the students. This job is being performed by educational data mining (EDM). EDM contains the methods that are used to discover the data in the educational environment and are used for understanding the student and their learning environment. The educational institutions are responsible and also at the same time curious to know about the performance of the students and teachers to know the current status of the functioning of the institution towards a better path. In this project, 3 models namely students assessments grades, final student performance, teachers performance. The result shows that both all the models will be showing an accurate result. A system is designed to predict the performance of the teachers based on the average of the grades of all the students, Students review and the staff members review are taken as input and the performance of the teachers is predicted accordingly. And at the same time, we will also be predicting the performance of the students based on their previous academic performance and gives suggestions.

Early Bird or Night Owl: Insights into Dutch Students’ Study Patterns using the Medical Faculty’s E-learning Registrations

Phenomenon : Educational activities for students are typically arranged without consideration of their preferences or peak performance hours. Students might prefer to study at different times based on their chronotype, aiming to optimize their performance. While face-to-face activities during the academic schedule do not offer flexibility and cannot reflect students’ natural learning rhythm, asynchronous e-learning facilitates studying at one’s preferred time. Given their ubiquitous accessibility, students can use e-learning resources according to their individual needs and preferences. E-learning usage data hence serves as a valuable proxy for certain study behaviors, presenting research opportunities to explore students’ study patterns. This retrospective study aims to investigate when and for how long undergraduate students used medical e-learning modules. Approach : We performed a cross-sectional analysis of e-learning usage at one medical faculty in the Netherlands. We used data from 562 undergraduate multimedia e-learning modules for pre-clinical students, covering various medical topics over a span of two academic years (2018/19 and 2019/20). We employed educational data mining approaches to process the data and subsequently identified patterns in access times and durations. Findings : We obtained data from 70,805 e-learning sessions with 116,569 module visits and 1,495,342 page views. On average, students used e-learning for 16.8 min daily and stopped using a module after 10.2 min, but access patterns varied widely. E-learning was used seven days a week with an hourly access pattern during business hours on weekdays. Across all other times, there was a smooth increase or decrease in e-learning usage. During the week, more students started e-learning sessions in the morning (34.5% vs. 19.1%) while fewer students started in the afternoon (42.6% vs. 50.8%) and the evening (19.4% vs. 27.0%). We identified ‘early bird’ and ‘night owl’ user groups that show distinct study patterns. Insights : This retrospective educational data mining study reveals new insights into the study patterns of a complete student cohort during and outside lecture hours. These findings underline the value of 24/7 accessible study material. In addition, our findings may serve as a guide for researchers and educationalists seeking to develop more individualized educational programs.

Educational Data Mining: Multiple Choice Question Classification in Vocational School

Data mining on student learning outcomes in the education sector can overcome this problem. This research aimed to provide a solution for selecting quality multiple choice questions (MCQ) using the results of students’ mid-semester exams in vocational high schools using a Data Mining approach. The research method used was the Cross-Industry Standard Process for Machine Learning (CRISP-ML) model. Steps to assess the accuracy of analyzing the difficulty level of questions based on student profile data and midterm test results. The data used in this research were the findings of basic computer tests on mid-term exams in mathematics disciplines at vocational high schools. This research used several classification algorithms, including SVM, Naive Bayes, Random Forest, Decision Three, Linear Regression, and KNN. The results of evaluating the classification

Assessing Students Performance Using Neutrosophic Tool

Recently, a lot of educational as well as academic researchers have shown their ultimate interest in educational data mining techniques. Thus, several studies that can definitely contribute to the improvement of the educational process are conducted. The results of this lead to several issues that have to be addressed if the students general academic performances are to be improved. In this paper, we investigate the academic performance of a set of students in their core subjects. This we did by using the concept of the neutrosophic frequency, as well as the neutrosophic relative frequency distribution for the class of scores for the set of students. The results give some form of expectation for their general performance. This case serves as a means to enhance the educational process of the chosen set of students by identifying the students at risk of failure or dropping out and predicting the students' academic level at an early stage to provide the necessary support for the at-risk students.

Student’s performance prediction based on an improved multi-view hypergraph neural network

ABSTRACT Predicting students’ academic performance is a crucial area of research in Educational Data Mining. Efficient performance prediction can significantly improve instructional effectiveness, facilitate personalised learning, and identify at-risk students. While researchers have analysed the complex relationships between students’ daily behaviours and their academic performance, most studies focus solely on individual student models and disregard potential relationships among students. To address these issues, we propose an improved multi-view hypergraph neural network (IMHNN). IMHNN employs hypergraphs to establish high-order relationships between student behaviours and introduces an attentional convolutional network to adaptively obtain weights for different behaviours. Additionally, a residual network is introduced to mitigate transition smoothing and improve the generalisation performance of the model. Using a genuine education dataset, we compare the performance of various approaches, demonstrating that our method outperforms other existing methods.

Investigation and the development of learning analytics dashboard in open and distance learning using big data mining

<p class="Abstract">The main aim of this study is to provide universities with a way of examining and predicting student performance. The fundamental aim and purpose of this study is to help academic institutions to analyse and predict student performance. The credibility and accuracy of the model was examined by comparing the predicted results of the model with the observed values. And educational data mining techniques were used to create student profiles. Weighted gain, classification analysis, decision tree and rule induction were used in this study. The results of the study showed that the level of students' academic performance varied according to criteria such as academic structure, faculty, mode of enrolment and gender. In order to determine the relative importance of variables, the information weight gain technique was used after generating rule induction parameters and hidden rules between data. Using data mining techniques, we can obtain both guidelines to instruct students and information to help us identify them.</p>

The treatment of error in learners of Russian as a foreign language: Visual analytics

There are well-known challenges in the assessment of learning in general, and especially in foreign language learning. The treatment of error in the classroom is a recent topic of research and one that has given rise to multiple approaches to pinpoint, identify and classify the errors made by learners of foreign and second languages. This article presents a methodological model based on visual analytics and education data mining to optimise teacher intervention in the face of individual and collective errors in the Russian language classroom. The methodology has been tested on learners of Russian as a foreign language at the University of Granada. It comprised an online questionnaire for skills assessment, with 75 questions that were classified by grammatical category and sub-category. It was filled out by the learners of the 2021/2022 academic year, yielding 31 responses. The responses were then analysed through visual analytics and education data mining techniques. Clustering questions and learners allowed the identification of different error patterns and groups of learners with common errors. This serves to demonstrate the usefulness of these techniques for classroom assessment.

Hyperscale data analysis oriented optimization mechanisms for higher education management systems platforms with evolutionary intelligence

Higher education institutions face vast amounts of complex data from various sources. Extracting meaningful insights from this data can improve student outcomes and institutional performance. This paper proposes novel evolutionary optimization mechanisms for higher education management systems to enable hyperscale data analysis. An integrated framework is developed, combining educational data mining, learning analytics, and evolutionary computation techniques. The methodology employs a multi-objective evolutionary algorithm with dynamic resource allocation to optimize multiple objectives simultaneously. Adaptive learning control is incorporated to balance exploration and exploitation. Theoretical analyses provide convergence proofs for the proposed algorithms. Comprehensive experiments on real-world and synthetic datasets demonstrate the effectiveness of the proposed mechanisms compared to state-of-the-art approaches. The results show significant performance gains regarding solution quality, scalability, and computational efficiency. The proposed techniques can be a foundation for developing the next generation of intelligent higher education management systems.