Educational Data Mining Research Articles

A Text Mining and Statistical Approach for Assessment of Pedagogical Impact of Students’ Evaluation of Teaching and Learning Outcome in Education

Technology-enhanced learning (TEL) is now at the heart of teaching and learning process in many higher education institutions (HEIs). Today, educators are faced with the challenges of pedagogically specifying what tools, methods, and technologies are used to support the teachers and students, and to help maintain/sustain a continuous education and practices. This study shows that there is an opportunity in the use of (educational) datasets derived about the teaching and learning processes to provide insights for fostering the education process. To this effect, it analyzed the students’ evaluation of teaching (SET) dataset ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$n=471968$ </tex-math></inline-formula> ) collected within a higher education setting to determine prominent factors that influences the students’ performance or the way (TEL-based) education is being delivered, including its didactical impact and implications for practice. Theoretically, the study employed a mixed methodology grounded on integration of the Data-structure approach and Descriptive decision theory to study the rationality behind the students’ evaluation of the teaching and performance. This was done through the Textual data quantification (qualitative) and Statistical (quantitative) analysis. Qualitatively, the study applied the Educational Process and Data Mining (EPDM) model (a text mining method) to extract the different sentiments and emotional valence expressed by the students in the SET, and how those characteristically differ based on the period and type of evaluation they have completed (between 2019 to 2021). For the quantitative analysis, the study used a multivariate analysis of covariance (MANCOVA) and multiple pairwise comparisons post-hoc tests to analyze the quantified information (average sentiment and emotional valence) extracted from the SET data to determine the marginal means of effect the different SET types and evaluation period have on the students’ learning outcomes/perception about the teaching-learning process. In addition, the study empirically discussed and shed light on the implications of the main findings for TEL-based Education, particularly implemented by the HEI during the analyzed periods. The scholastic indicator from the study shows that while the flexible digital models or instructional methods are effective for continuous education, innovative pedagogies, and teaching transformations. It also, on the other hand, serve as an incentive for more robust research that idiosyncratically look into their implications for the students’ learning outcomes and assessment done in this study.

Methods of Overcoming Data Waste in Education: A Systematic Review

This research aimed to perform a systematic review of recent scientific studies that addressed the topic of educational data mining by highlighting recent research trends and reviewing the best practices of smart technology in this field. The current research was restricted to scientific studies and conferences in English that were published through the IEEE database between 2020 and October 2022. After applying the PRISMA form and reviewing and documenting the method, 25 papers were identified that matched the criteria. The outcomes of the current research concluded that the trend of prediction was one of the most common research trends in the domain of educational data mining. Moreover, this trend varied remarkably in its coverage of educational scientific aspects. On the other hand, the outcomes demonstrated that the trend of recommending the most appropriate specialised tracks for learners was one of the least common research trends. With regard to intelligent technical practices, the outcomes of the research revealed that the most used and mature intelligent technologies in practical frameworks and algorithms were intended for prediction purposes, and these were shown to greatly enhance researchers’ ability to reach accurate and logical results that are applicable in real educational contexts. KEYWORDS Artificial intelligence, machine learning, algorithms, neural networks, educational data, educational institutions

Using data mining techniques to predict university student's ability to graduate on schedule

Research in educational data mining to establish or predict the retention of students in higher education institutions, as well as predict graduation performance abounds. This research is a data mining based project aimed at generating a model that can be used for predicting student's ability to graduate on time. In this research we have examined various factors such as age, gender, continuous assessment results, and final exam results, determine how they influence a student's graduation schedule. We have demonstrated our application of classification as a data mining technique to identify interesting patterns, and subsequently use predictive techniques to predict the possible consequent outcome, and further have conducted a detailed examination of the J48, Bayes Net, PART and Random Forest predictive algorithms and compared to draw conclusions on the data mining prediction tools that give optimum results. The J48 stood out in terms of performance output.

Classification and prediction of student performance data using various machine learning algorithms

In today's competitive world, it is critical for an institute to forecast student performance, classify individuals based on their talents, and attempt to enhance their performance in future tests. Students should be advised well in advance to concentrate their efforts in a specific area in order to improve their academic achievement. This type of analysis assists an institute in lowering its failure rates. Based on their prior performance in comparable courses, this study predicts students' performance in a course. Data mining is a collection of techniques used to uncover hidden patterns in massive amounts of existing data. These patterns may be valuable for analysis and prediction. Education data mining refers to the collection of data mining applications in the field of education. These applications are concerned with the analysis of data from students and teachers. The analysis might be used for categorization or prediction. Machine learning such as Nave Bayes, ID3, C4.5, and SVM are investigated. UCI machinery student performance data set is used in experimental study. Algorithms are analysed on certain parameters like- accuracy, error rate.

A Novel Approach to Predict Students Performance through Machine Learning

Forecasting student success can enable teachers to prevent students from dropping out before final examinations, identify those who need additional help and boost institution ranking and prestige. Machine learning techniques in educational data mining aim to develop a model for discovering meaningful hidden patterns and exploring useful information from educational settings. The key traditional characteristics of students (demographic, academic background and behavioral features) are the main essential factors that can represent the training dataset for supervised machine learning algorithms. The real goal is to have an overview of the systems of artificial intelligence that were used to predict Academic learning. This research also focuses on how to classify the most relevant attributes in student data by using prediction algorithm. Using educational machine learning methods, we could potentially improve the performance and progress of students more efficiently in an efficient manner. Students, educator and academic institutions could benefit and also have an impact. In this paper, two predictive models have been designed namely students’ assessments grades and final students’ performance. The models can be used to detect the factors that influence students’ learning achievement in MOOCs. The result shows that both models gain feasible and accurate results. The lowest RSME gain by RF acquire a value of 8.131 for students assessments grades model while GBM yields the highest accuracy in final students’ performance, an average value of 0.086 was achieved.

Using Big Data in Education: Curriculum Review with Educational Data Mining

Today, most educational institutions have become more interested in big data. Because the importance of extracting useful information from educational data to support decision-making on educational issues has increased day by day. In this context, through educational data mining, this research study aims to reveal the association rules among compulsory courses in the Computer Education and Instructional Technology curriculum within the faculty of education of a state university in Turkey. In this context, the research was conducted with data obtained from 258 preservice teachers who had completed all of their compulsory courses (n = 42) for the Computer Education and Instructional Technology curriculum, having graduated from the Computer Education and Instructional Technology program between 2012 and 2020. According to the experimental results, the academic performance of preservice teachers in some courses could be used as a predictor of their academic performance in other courses. Other findings from the study are discussed in detail, and suggestions put forth for future research.

Data pipelines for educational data mining in distance education

ABSTRACT New challenges in education demand effective solutions. Although Learning Analytics (LA), Educational Data Mining (EDM) and the use of Big Data are often presented as a panacea, there is a lot of ground to be covered in order for the EDM to answer the real questions of educators. An important step toward this goal is to implement holistic solutions that allow educational stakeholders to engage in the core of the EDM processes. The effectiveness of such an attempt relies on (a) having access to data arranged in an organized and meaningful way and (b) setting a sequence of processes that are flexible and reusable. Therefore, a data pipeline that imports data from a specially developed data warehouse is designed and created. Additionally, it is tested in real-life data, and results are discussed.

Exploring the Research Trend on Student Performance in Education Computing: A Bibliometric Analysis

The purpose of the study is to present a bibliometric analysis of the academic publication trends of student performance in education computing. These data were collected from the Scopus database that was published from 2012 to 2022. In the bibliometric analysis, important visual map and tables were produced to show publication trends from five different viewpoints including annual publications, countries, authors, publication sources, and keywords. The analysis results showed that the number of publications had increased rapidly by year during 2015 to 2019. The top countries include the United States, China, and India. Most of these publications were conference papers, and there are also article journals. The keyword co-occurrence analysis revealed that the research hotspots highlighted in this field were educational data mining, academic performance, classification and data mining mechanisms. Through this bibliometric research work, it can be expected that more researchers or scholars concentrating on utilizing two important algorithms; machine learning and deep learning, for analysing and forecasting student performance in higher educational computing institutions.

Performance Analysis of Agriculture Students in Adapting to Distance Learning During COVID-19 Pandemic through Educational Data Mining (EDM) Technique

Performance Analysis of Agriculture Students in Adapting to Distance Learning During COVID-19 Pandemic through Educational Data Mining (EDM) Technique

Analysis and Prediction of Student Performance by Using A Hybrid Optimized BFO-ALO Based Approach

Data mining offers effective solutions for a variety of industries, including education. Research in the subject of education is expanding rapidly because of thebigquantityof student data that can be utilized to uncover valuable learning behavior patterns. This research presents a method for forecasting the academic presentation of students in Portuguese as well as math subjects, and it is describing with the help of 33 attributes. Forecasting the educationalattainment of students is the most popular field of study in the modern period. Previous research has employed a variety of categorization algorithms to forecast student performance. Educational data mining is a topic that needs a lot of research to improve the precision of the classification technique and predict how well students will do in school. In this study, we made a method to predict how well a student will do that uses a mix of optimization techniques. BFO and ALO-based popular optimization techniques were applied to the data set. Python was used to process all the files and conduct a performance comparison analysis. In this study, we compared our model's performance with various existing baseline models and examined the accuracy with which the hybrid algorithm predicted the student data set. To verify the expected classification accuracy, a calculation was performed. The experiment's findings indicate that the BFO-ALO Based hybrid model, which, out of all the methods, with a 94.5 percent success rate, is the preferred choice.

Predicting Master’s students’ academic performance: an empirical study in Germany

The tremendous growth in electronic educational data creates the need to have meaningful information extracted from it. Educational Data Mining (EDM) is an exciting research area that can reveal valuable knowledge from educational databases. This knowledge can be used for many purposes, including identifying dropouts or weak students who need special attention and discovering extraordinary students who can be offered lifetime opportunities. Although former studies in EDM used an extensive range of features for predicting students’ academic achievement (in terms of (i) achieved grades or (ii) passing and failing), those features are sometimes not obtainable for practical usage, and therefore, the prediction models are not feasible for employment. This study uses data mining (DM) algorithms to predict the academic performance of master’ s students by using a non-extensive data set and including only the features that are easy to collect at the beginning of a studying program. To perform this study, we have collected over 700 students' records from 2010 to 2018 from the Faculty of Business Informatics and Mathematics at the University of Mannheim in Germany. Those records include demographics and post-enrollment features such as semester grades. The empirical results show the following: (i) the most significant features for predicting students' academic achievements are the students’ grades in each semester (importance rate between 14 and 36%), followed by the distance from students’ accommodation to university (importance rate between 6 and 18%) and culture (importance rate between 7 and 17%). On the other hand, gender, age, the numbers of failed courses, and the number of registered and unregistered exams per semester are less significant for the predictions. (ii) As expected, predictions performed after the second semester is more accurate than those performed after the first semester. (iii) Unsurprisingly, models that predict two classes yield better results than those that predict three. (iv) Random Forest classifier performs the best in all prediction models (0.77–0.94 accuracy), and using oversampling methods to deal with imbalanced data can significantly improve the performance of DM methods. For future work, we recommend testing the predictive models on other master programs and a larger datasets. Furthermore, we recommend investigating other oversampling approaches.

Feedback Generation through Artificial Intelligence

Feedback is an essential part of the educational assessment that improves student learning. As education changes with the advancement of technology, educational assessment has also adapted to the advent of Artificial Intelligence (AI). Despite the increasing use of online assessments during the last decade, a limited number of studies have discussed the feedback generation process as implemented through AI. To address this gap, we propose a conceptual paper to organize and discuss the application of AI in the feedback generation and delivery processes. Among different branches of AI, Natural Language Processing (NLP), Educational Data Mining (EDM), and Learning Analytics (LA) play the most critical roles in the feedback generation process. The process begins with analyzing students’ data from educational assessments to build a predictive machine learning model with additional features such as students’ interaction with course material using EDM methods to predict students’ learning outcomes. Written feedback can be generated from a model with NLP-based algorithms before being delivered, along with non-verbal feedback via a LA dashboard or a digital score report. Also, ethical recommendations for using AI for feedback generation are discussed. This paper contributes to understanding the feedback generation process to serve as a venue for the future development of digital feedback.

Educational data mining in the academic setting: employing the data produced by blended learning to ameliorate the learning process

PurposeThe purpose of this paper is to introduce an interactive system that relies on the educational data generated from the online Universities services to assess, correct and ameliorate the learning process for both students and faculty.Design/methodology/approachIn the presented research, data from the online services, provided by a Greek University, prior, during and after the COVID-19 outbreak, are analyzed and utilized in order to ameliorate the offered learning process and provide better quality services to the students. Moreover, according to the learning paths, their presence online and their participation in the services of the University, insights can be derived for their performance, so as to better support and assist them.FindingsThe system can deduce the future learning progression of each student, according to the past and the current performance. As a direct consequence, the exploitation of the data can provide a road map for the strategic planning of universities, can indicate how the learning process can be updated and amended, both online and in person, as well as make the learning experience more essential, effective and efficient for the students and aiding the professors to provide a more meaningful and to-the-point learning experience.Originality/valueNowadays, educational activities in academia are strongly supported by online services, information systems and online educational materials. The learning design in the academic setting is primarily facilitated in the University premises. However, the exploitation of the contemporary technologies and supporting materials that are available online can enrich and transform the educational process and its results.

Predicting Students' Performance in Final Examination using Deep Neural Network

The academic result is the most important thing in a student's career. This result depends on their academic performance and many other factors. Educational data mining can help both students and institutions develop their academic performance. For analysis of their performance, we can use new techniques Deep Learning, Convolution Neural Networks, Data Clustering, Optimization Algorithms, etc. In machine learning. Using Deep Learning, we will predict the student’s performance yearly in the form of CGPA and compare that with the real CGPA. A real dataset can boost the prediction performance. We used a real dataset from the Institute of Science, Trade &amp; Technology (ISTT). We used a total of 18 data factors to predict the performance and the data factors are: Class Performance, Test Marks, Class Attendance, Due Time Assignment Submission, Lab Performance, Previous Semester Result, Family Education, Freelancer, Relationship with Faculty, Study Hours, Living Area, Social Media Attraction, Extra-Curricular Activity, Drug Addiction, Financial Support from Family, Political Involvement, Affair &amp; Year Final Result.

Recent advances in Predictive Learning Analytics: A decade systematic review (2012-2022).

The last few years have witnessed an upsurge in the number of studies using Machine and Deep learning models to predict vital academic outcomes based on different kinds and sources of student-related data, with the goal of improving the learning process from all perspectives. This has led to the emergence of predictive modelling as a core practice in Learning Analytics and Educational Data Mining. The aim of this study is to review the most recent research body related to Predictive Analytics in Higher Education. Articles published during the last decade between 2012 and 2022 were systematically reviewed following PRISMA guidelines. We identified the outcomes frequently predicted in the literature as well as the learning features employed in the prediction and investigated their relationship. We also deeply analyzed the process of predictive modelling, including data collection sources and types, data preprocessing methods, Machine Learning models and their categorization, and key performance metrics. Lastly, we discussed the relevant gaps in the current literature and the future research directions in this area. This study is expected to serve as a comprehensive and up-to-date reference for interested researchers intended to quickly grasp the current progress in the Predictive Learning Analytics field. The review results can also inform educational stakeholders and decision-makers about future prospects and potential opportunities.

Analytics for Game-Based Learning

The purpose of this special section is to collect in one place how data in game-based learning environments may be turned into valuable analytics for student assessment, support of learning, and/or improvement of the game, using existing or emerging empirical research methodologies from various fields, including computer science, software engineering, educational data mining, learning analytics, learning sciences, statistics, and information visualization. Four contributions form this special section, which will inspire future high-quality research studies and contribute to the growing knowledge base of learning analytics and game-based learning research and practice.

Random Forest Analysis of Factors Predicting Science Achievement Groups: Focusing on Science Activities and Learning in School

Abstract This study explored science-related variables that have an impact on the prediction of science achievement groups by applying the educational data mining (EDM) method of the random forest analysis to extract factors associated with students categorized in three different achievement groups (high, moderate, and low) in the Korean data from the 2015 Programme for International Student Assessment (PISA). The 57 variables of science activities and learning in school collected from PISA questionnaires for students and parents were analyzed. Variables related to students’ past science activities, science teaching and learning methods, and environmental awareness were found to played important roles in predicting science achievement. When checking partial dependence plots for major variables, science activities and instructional strategies had a high probability of changing the prediction of an achievement group. This study focused on science-related contextual variables that can be improved through government policies and science teachers’ efforts in the classroom.

Project-Based Learning Guidelines for Health Sciences Students: An Analysis with Data Mining and Qualitative Techniques

Academic leaders all over the world are encouraging the use of active methodologies in teaching, especially in higher education. The reason for this is that social changes are happening at an ever-increasing rate, and they require students and teachers to develop digital skills. This is especially significant for health sciences degrees, in which future graduates must have effective problem-solving skills. To respond to this challenge, the use of a project-based learning (PBL) methodology, together with various monitoring techniques based on the use of Educational Data Mining (EDM) and mixed methods, will provide teachers with information about the effectiveness of the methodology and guide the implementation of personalized educational responses. This study provides a protocol for the application of the PBL methodology in e-Learning and blended-Learning (b-Learning) teaching modalities for health sciences students studying occupational therapy in higher education. In addition, statistical techniques for the analysis of covariance and unsupervised learning allow differences to be detected between the two teaching modalities, thus specifying their effectiveness in terms of a range of variables related to behavioral patterns, performance, and satisfaction. Data visualization also helps in understanding the qualitative aspects of the learning process. These data will help teachers to produce more effective proposals for the implementation of the PBL methodology based on the based on the context of the teaching-learning process. Therefore, this protocol offers many resources and materials to help teachers implement the PBL methodology in e-Learning and b-Learning teaching methods.

Mining Sequential Learning Trajectories With Hidden Markov Models For Early Prediction of At-Risk Students in E-Learning Environments

With the onset of online education via technology-enhanced learning platforms, large amount of educational data is being generated in the form of logs, clickstreams, performance, etc. These Virtual Learning Environments provide an opportunity to the researchers for the application of educational data mining and learning analytics, for mining the students learning behavior. This further helps them in data-driven decision making through timely intervention via early warning systems (EWS), reflecting and optimizing educational environments, and refining pedagogical designs. In this, the role of EWS is to timely identify the at-risk students. This study proposes a modeling methodology deploying interpretable Hidden Markov Model for mining of the sequential learning behavior built upon derived performance features from light-weight assessments. The public OULA dataset having diversified courses and 32 593 student records is used for validation. The results on the unseen test data achieve a classification accuracy ranging from 87.67% to 94.83% and AUC from 0.927 to 0.989, and outperforms other baseline models. For implementation of EWS, the study also predicts the optimal time-period, during the first and second quarter of the course with sufficient number of light-weight assessments in place. With the outcomes, this study tries to establish an efficient generalized modeling framework that may lead the higher educational institutes toward sustainable development.

Enticing Correlation between Motivation and Self-Regulation: A Novel Approach for Academic Excellence

Abstract: Today, we can easily say that there is no limit to the size of the data that exists in the real world-it can be in tens, hundreds, thousands, billions or even trillions of dimensions. However, not all dimensions are vital or relevant for a more detailed analysis. The key objective of educational data mining is to analyze educational data to solve educational and research problems. Our research in this paper focuses primarily on identifying relevant characteristics that can help determine the academic performance of students. The selection of features carried out as data preprocessing techniques keeping in mind the key idea to eliminate irrelevant and redundant features and thus selecting the optimal characteristics that can improve the overall accuracy of the model. The characteristics selected through the selection of functions can help to predict the academic performance of the student in several colleges and universities, which is one of the most imperative contemplations by interested parties to build and maintain a quality system. Although there are several studies that determine the factors that affect the academic performance of students, there is still a gap in existing research that focuses on the psychological factors of a student. The document is structured as follows. Section two contains a brief explanation about the related work in this field. In section three, we have discussed the adopted methodology that presents the data set, the feature selection algorithms, and the characteristic evaluation approach. Section four presents the configuration and experimental results and section five focuses on the conclusion and future scope.