Student Performance Prediction Research Articles

Blending E-Learning with Hands-on Laboratory Instruction in Engineering Education

Among the various information sources exploited for the improvement of the learning process and outcomes, access and usage data from the interaction of students with e-learning platforms along with (past) student performance data are established as the two most meaningful and informative groups of variables. In the present study, these two groups of variables are jointly investigated as to their efficiency in providing both accurate and early prediction of student performance and behavior. The relevant educational intervention is designed and implemented as a quasi-experiment with undergraduate Electrical and Electronics Engineering students, under a novel approach that blends e-learning (asynchronous e-study and synchronous e-assessment) with a hands-on laboratory component. Can educational data mining algorithms provide both early and accurate prediction of student performance and student behavior under this scenario? If yes, how much prediction accuracy can be traded for prediction timeliness in order to allow a proactive class instructor take supportive measures for weak/marginal students, implementing a ‘self-contained’ strategy? To answer these questions, real data from the interaction of 3 academic year student cohorts with moodle are collected and analyzed. Results reveal that the proposed scenario can afford both accurate and early prediction of student performance and behavior, on the basis of data collected within the running academic term. The middle of the term is indicated as the earliest time point for getting meaningful predictions. Moreover, clustering of the data in the selected feature space reveals a consistent and therefore exploitable behavior of students along the term.

Recurrent Neural Network-FitNets: Improving Early Prediction of Student Performanceby Time-Series Knowledge Distillation

This study helps improve the early prediction of student performance by RNN-FitNets, which applies knowledge distillation (KD) to the time series direction of the recurrent neural network (RNN) model. The RNN-FitNets replaces the teacher model in KD with “an RNN model with a long-term time-series in which the features during the entire course are inputted” and the student model in KD with “an RNN model with a short-term time-series in which only the features during the early stages are inputted.” As a result, the RNN model in the early stage was trained to output the same results as the more accurate RNN model in the later stages. The experiment compared RNN-FitNets with a normal RNN model on a dataset of 296 university students in total. The results showed that RNN-FitNets can improve early prediction. Moreover, the SHAP value was employed to explain the contribution of the input features to the prediction results by RNN-FitNets. It was shown that RNN-FitNets can consider the future effects of the input features from the early stages of the course.

A survey on deep learning based knowledge tracing

“Knowledge tracing (KT)” is an emerging and popular research topic in the field of online education that seeks to assess students’ mastery of a concept based on their historical learning of relevant exercises on an online education system in order to make the most accurate prediction of student performance. Since there have been a large number of KT models, we attempt to systematically investigate, compare and discuss different aspects of KT models to find out the differences between these models in order to better assist researchers in this field. The findings of this study have made substantial contributions to the progress of online education, which is especially relevant in light of the current global pandemic. As a result of the current expansion of deep learning methods over the last decade, researchers have been tempted to include deep learning strategies into KT research with astounding results. In this paper, we evaluate current research on deep learning-based KT in the main categories listed below. In particular, we explore (1) a granular categorisation of the technological solutions presented by the mainstream Deep Learning-based KT Models. (2) a detailed analysis of techniques to KT, with a special emphasis on Deep Learning-based KT Models. (3) an analysis of the technological solutions and major improvement presented by Deep Learning-based KT models. In conclusion, we discuss possible future research directions in the field of Deep Learning-based KT.

Student Performance Prediction using Machine Learning Algorithms: A Review

Student Performance Prediction using Machine Learning Algorithms: A Review

Predicting At-Risk Students Using Weekly Activities and Assessments

Abstract— Although Online learning has been so popular especially during epidemic crisis, it has a drawback of high dropouts and low completion rates. Institutes search for ways to support their students learning and increase completion rates. Institutes will be able to predict students’ performances and make interventions on time if they have some analytical strategy. Yet, efficient prediction and proactive intervention depends on using meaningful, reliable, and accurate data. Institutes different tools like Virtual Learning Environment (VLE) for teaching and content delivery. These tools provide large databases that are useful to improve prediction of students’ performance research. In this study, an Open University course VLE data is analyzed to investigate if weekly engagement alone, integrated with assessments scores (first approach), and accumulated previous assessments up to a certain week data ((second approach) lead to accurate student performance prediction. Importance of VLE data is highlighted here, which sheds light on students’ haviour and leads to developing models that can predict student’s outcome accurately. Second approach generated robust prediction models which outperformed the results obtained using first approach.

Early prediction of student knowledge in game‐based learning with distributed representations of assessment questions

AbstractGame‐based learning environments hold significant promise for facilitating learning experiences that are both effective and engaging. To support individualised learning and support proactive scaffolding when students are struggling, game‐based learning environments should be able to accurately predict student knowledge at early points in students' gameplay. Student knowledge is traditionally assessed prior to and after each student interacts with the learning environment with conventional methods, such as multiple choice content knowledge assessments. While previous student modelling approaches have leveraged machine learning to automatically infer students' knowledge, there is limited work that incorporates the fine‐grained content from each question in these types of tests into student models that predict student performance at early junctures in gameplay episodes. This work investigates a predictive student modelling approach that leverages the natural language text of the post‐gameplay content knowledge questions and the text of the possible answer choices for early prediction of fine‐grained individual student performance in game‐based learning environments. With data from a study involving 66 undergraduate students from a large public university interacting with a game‐based learning environment for microbiology, Crystal Island, we investigate the accuracy and early prediction capacity of student models that use a combination of gameplay features extracted from student log files as well as distributed representations of post‐test content assessment questions. The results demonstrate that by incorporating knowledge about assessment questions, early prediction models are able to outperform competing baselines that only use student game trace data with no question‐related information. Furthermore, this approach achieves high generalisation, including predicting the performance of students on unseen questions. Practitioner notesWhat is already known about this topic A distinctive characteristic of game‐based learning environments is their capacity to enable fine‐grained student assessment. Adaptive game‐based learning environments offer individualisation based on specific student needs and should be able to assess student competencies using early prediction models of those competencies. Word embedding approaches from the field of natural language processing show great promise in the ability to encode semantic information that can be leveraged by predictive student models. What this paper adds Investigates word embeddings of assessment question content for reliable early prediction of student performance. Demonstrates the efficacy of distributed word embeddings of assessment questions when used by early prediction models compared to models that use either no assessment information or discrete representations of the questions. Demonstrates the efficacy and generalisability of word embeddings of assessment questions for predicting the performance of both new students on existing questions and existing students on new questions. Implications for practice and/or policy Word embeddings of assessment questions can enhance early prediction models of student knowledge, which can drive adaptive feedback to students who interact with game‐based learning environments. Practitioners should determine if new assessment questions will be developed for their game‐based learning environment, and if so, consider using our student modelling framework that incorporates early prediction models pretrained with existing student responses to previous assessment questions and is generalisable to the new assessment questions by leveraging distributed word embedding techniques. Researchers should consider the most appropriate way to encode the assessment questions in ways that early prediction models are able to infer relationships between the questions and gameplay behaviour to make accurate predictions of student competencies.

Research on Student Performance Prediction Based on Stacking Fusion Model

Online learning is gradually becoming popular with the continuous development of Internet technology and the rapid development of educational informatization. It plays a key role in predicting students’ course performance based on their online learning behavior. It can optimize the effects of teaching and improve teaching strategies. Student performance prediction models that are built with a single algorithm currently have limited prediction accuracy. Meanwhile, model fusion improvement technology can combine many algorithms into a single model, thereby enhancing the overall effect of the model and providing better performance. In this paper, a stacking fusion model based on RF-CART–XGBoost–LightGBM is proposed. The first layer of the model uses a decision tree (CART), random forest, XGBoost and LightGBM as the base models. The second layer uses the LightGBM model. We used the Kalboard360 student achievement dataset, and features related to online learning behavior were selected as the model’s input for model training. Finally, we employed five-fold cross-validation to assess the model’s performance. In comparison with the four single models, the two fusion models based on the four single models both show significantly better performance. The prediction accuracies of the bagging fusion model and stacking fusion model are 83% and 84%, respectively. This proves that the proposed stacking fusion model has better performance, which helps to improve the accuracy of the performance prediction model further. It also provides an effective basis for optimizing the effects of teaching.

Determinants and Prediction of Secondary Students Performance in Mathematics in Portugal Using Machine Learning

Mathematics brings order and prevents chaos in our lives. Power of reasoning, inventiveness, abstract or spatial thinking, critical thinking, problem-solving abilities, and even excellent communication skills are some of the attributes that mathematics fosters. The purpose of this research is to identify the factors that impact students' mathematics performance. Simultaneously, this study tries to predict student's mathematics performance. The secondary information was gathered from https://archive.ics.uci.edu/ml/datasets/student+performance#. This study uses a variety of methodologies such as percentage distribution, association tests, association rule mining, Decision tree, Random Forest, Support Vector Machine, Naive Bayes, K-Nearest-Neighbors, Linear Discriminant Analysis, Neural Network, and Logistic Regression. Students whose father's education is higher, mother's education is higher, mothers' occupation services, who rarely go out with friends, and who did not fail the previous class have considerably better mathematics performance. Students whose father has a primary education, who spend a lot of time with friends, drink alcohol during the workday, and live in rural areas have poor mathematics performance. Furthermore, in this case, the best classifier for prediction is a Neural Network. Therefore, the performance of students in mathematics depends on the characteristics of the students as well as the characteristics of their parents and place of residence. The government and other NGOs must step forward to educate the country's people about these critical factors. Keywords: Determinant, Prediction, Student, Performance, Machine, Learning. DOI: 10.7176/CEIS/13-5-03 Publication date: October 31 st 2022

Difference of Probability and Information Entropy for Skills Classification and Prediction in Student Learning

The probability of an event is in the range of [0, 1]. In a sample space S, the value of probability determines whether an outcome is true or false. The probability of an event Pr(A) that will never occur = 0. The probability of the event Pr(B) that will certainly occur = 1. This makes both events A and B thus a certainty. Furthermore, the sum of probabilities Pr(E1) + Pr(E2) + … + Pr(En) of a finite set of events in a given sample space S = 1. Conversely, the difference of the sum of two probabilities that will certainly occur is 0. Firstly, this paper discusses Bayes’ theorem, then complement of probability and the difference of probability for occurrences of learning-events, before applying these in the prediction of learning objects in student learning. Given the sum total of 1; to make recommendation for student learning, this paper submits that the difference of argMaxPr(S) and probability of student-performance quantifies the weight of learning objects for students. Using a dataset of skill-set, the computational procedure demonstrates: i) the probability of skill-set events that has occurred that would lead to higher level learning; ii) the probability of the events that has not occurred that requires subject-matter relearning; iii) accuracy of decision tree in the prediction of student performance into class labels; and iv) information entropy about skill-set data and its implication on student cognitive performance and recommendation of learning [1].

Predicting individual learning performance using machine‐learning hybridized with the teaching‐learning‐based optimization

AbstractReliable prediction of individual learning performance can facilitate timely support to students and improve the learning experience. In this study, two well‐known machine‐learning techniques, that is, support vector machine (SVM) and artificial neural network (ANN), are hybridized by teaching–learning‐based optimizer (TLBO) to reliably predict the student exam performance (fail‐pass classes and final exam scores). For the defined classification and regression problems, the TLBO algorithm carries out the feature selection process of both ANN and SVM techniques in which the optimal combination of the input variables is determined. Moreover, the ANN architecture is determined using the TLBO algorithm parallel to the feature selection process. Finally, four hybrid models containing anonymized information on both discrete and continuous variables were developed using a comprehensive data set for learning analytics. This study provides scientific utility by developing hybridized machine‐learning models and TLBO, which can improve the predictions of student exam performance. In practice, individual performance prediction can help to advise students about their academic progress and to take appropriate actions such as dropping units in subsequent teaching periods. It can also help scholarship providers to monitor student progress and provision of support.

Standing on the shoulders of giants: Online formative assessments as the foundation for predictive learning analytics models

AbstractAs universities around the world have begun to use learning management systems (LMSs), more learning data have become available to gain deeper insights into students' learning processes and make data‐driven decisions to improve student learning. With the availability of rich data extracted from the LMS, researchers have turned much of their attention to learning analytics (LA) applications using educational data mining techniques. Numerous LA models have been proposed to predict student achievement in university courses. To design predictive LA models, researchers often follow a data‐driven approach that prioritizes prediction accuracy while sacrificing theoretical links to learning theory and its pedagogical implications. In this study, we argue that instead of complex variables (e.g., event logs, clickstream data, timestamps of learning activities), data extracted from online formative assessments should be the starting point for building predictive LA models. Using the LMS data from multiple offerings of an asynchronous undergraduate course, we analysed the utility of online formative assessments in predicting students' final course performance. Our findings showed that the features extracted from online formative assessments (e.g., completion, timestamps and scores) served as strong and significant predictors of students' final course performance. Scores from online formative assessments were consistently the strongest predictor of student performance across the three sections of the course. The number of clicks in the LMS and the time difference between first access and due dates of formative assessments were also significant predictors. Overall, our findings emphasize the need for online formative assessments to build predictive LA models informed by theory and learning design. Practitioner notesWhat is already known about this topic Higher education institutions often use learning analytics for the early identification of low‐performing students or students at risk of dropping out. Most predictive models in learning analytics rely on immutable student characteristics (e.g., gender, race and socioeconomic status) and complex variables extracted from log data within a learning management system. Prioritizing prediction accuracy without theory orientation often yields “black‐box” models that fail to inform educators on what remedies need to be taken to improve student learning. What this paper adds Predictive models in learning analytics should consider learning theory, pedagogy and learning design to identify key predictors of student learning. Online formative assessments can be a starting point for building predictive models that are not only accurate but also provide educators with actionable insights on how student learning can be improved. Time‐related and score‐related features extracted from online formative assessments are particularly useful for predicting students' course performance. Implications for practice and/or policy This study provides strong evidence for using online formative assessments as the foundation for predictive models in learning analytics. Student data from online formative assessments can help educators provide students with feedback while informing future formative assessment cycles. Higher education institutions should avoid the hype around complex data from learning management systems and instead rely on effective learning tools such as online formative assessments to revolutionize the use of learning analytics.

ContextKT: A Context-Based Method for Knowledge Tracing

Knowledge tracing, which is used to predict students’ performance based on their previous practices, has attracted many researchers’ attention. Especially in this rising period of intelligent education, many knowledge tracing methods have been developed. However, most of the existing knowledge tracing methods focus on the personality of practices and knowledge concepts but ignore the contexts related to the studying process. In this paper, we propose a context-based knowledge tracing model, which combines students’ historical performance and their studying contexts during knowledge mastery. To be specific, we first define five studying contexts for performance prediction. The basic context is the current knowledge state of a student, which is described by their practice sequences. Then, a QR-matrix is defined to represent the relationship among questions, knowledge concepts, and responses, which describes the contexts of questions and knowledge. Furthermore, an improved LSTM model is proposed to capture the context of students’ memory and forgetness, and a multi-head attention mechanism is designed to capture the context of students’ behaviors. Finally, based on the captured contexts, the prediction model ContextKT is established. Our prediction model is evaluated on two real educational datasets. The experimental results show our model is effective and efficient in student performance prediction, and it outperforms the other existing methods.

Predicting Student Performance from Video-Based Learning System: A Case Study

Predicting Student Performance from Video-Based Learning System: A Case Study

Editorial

It gives me great pleasure to announce the eighth regular issue of 2022. In this issue, 4 papers cover various topical aspects of computer science by 12 authors from 5 countries. In an ongoing effort to further strengthen our journal, I would like to expand the editorial board: If you are a tenured associate professor or above with a strong publication record, you are welcome to apply to join our editorial board. We are also interested in high-quality proposals for special issues on new topics and trends. As always, I would like to thank all the authors for their sound research and the editorial board for their extremely valuable review effort and suggestions for improvement. These contributions, together with the generous support of the consortium members, sustain the quality of our journal. In the second regular issue, I am very pleased to introduce the following 4 accepted articles: Sanam Fida, Nayyer Masood and Nirmal Tariq from Pakistan, and Faiza Qayyum from the Republic of Korea address in their joint research a novel hybrid ensemble clustering technique for student performance prediction. In a research collaboration between India and Greece, Banani Ghose, Zeenat Rehena and Leonidas Anthopoulos discuss a Deep Learning-based technique for predicting air quality using influencing pollutants of neighboring locations in a smart city environment. Marloes Vredenborg, Daan Sutmuller, Mariëlle den Hengst-Bruggeling, and Judith Masthoff from the Netherlands introduce an exploratory study on a system to reduce information overload and tunnel vision in homicide investigations. And last but not least, Wim Westera from the Netherlands presents three computational scoring models that take into account the number of attempts that a player makes to be successful. Enjoy Reading!

A Novel Hybrid Ensemble Clustering Technique for Student Performance Prediction

Educational Data Mining (EDM) is a branch of data mining that focuses on extraction of useful knowledge from data generated through academic activities at school, college or at university level. The extracted knowledge can help to perform the academic activities in a better way, so it is useful for students, parents and institutions themselves. One common activity in EDM is students grade prediction with an aim to identify weak or at-risk students. An early identification of such students helps to take supportive measures that may help students to improve. Among a vast number of approaches available in this field, this study mainly focuses on generating a smarter dataset through reduced feature set without compromising the number of records in it and then producing an approach which combines the strengths of classification and clustering for better prediction results. In this study it has been identified that individual features have distinct effect and that removing misclassified data can affect the overall results. Backward selection is adopted using Pearson correlation as a metric to produce smarter dataset with lesser attributes and better accuracy in prediction. After feature set selection, we have applied EMT (Ensemble Meta-Based Tree Model) classification on it to identify best performing classifiers from five families of classifiers. In hybrid approach, first the ensemble clustering is applied on smart dataset and then EMT classification is applied to reevaluate the un-clustered data, which gives a boost in performance and provides us an accuracy of 93%.

PREDIKSI KINERJA MAHASISWA DALAM PERKULIAHAN DARING BERBASIS E-LEARNING MENGGUNAKAN METODE LOGISTIC REGRESSION

There are many problems that occur in the online learning process, one of which is the difficulty of students in understanding the material well. Various efforts have been declared by lecturers to support online learning, starting from direct material explanations through OpenLearning, Zoom, and Google Meet media. To find out whether the student's performance in this online lecture is good or not. Prediction of student performance in online lectures is used as one of the supports for evaluation decisions at the University of Muhammadiyah, East Kalimantan. The purpose of this study is to determine indicators, implement and evaluate the performance of the Logistic Regression algorithm using the confusion matrix to see student performance in online lectures. The number of data used in this study was 2663 data on odd semester citizenship courses in 2020/2021 and 2021/2022. . The results of the Logistic Regression algorithm using 80% training data sharing and 20% testing data obtained an accuracy value of 91.66%.

Early-warning prediction of student performance and engagement in open book assessment by reading behavior analysis

Digitized learning materials are a core part of modern education, and analysis of the use can offer insight into the learning behavior of high and low performing students. The topic of predicting student characteristics has gained a lot of attention in recent years, with applications ranging from affect to performance and at-risk student prediction. In this paper, we examine students reading behavior using a digital textbook system while taking an open-book test from the perspective of engagement and performance to identify the strategies that are used. We create models to predict the performance and engagement of learners before the start of the assessment and extract reading behavior characteristics employed before and after the start of the assessment in a higher education setting. It was found that strategies, such as: revising and previewing are indicators of how a learner will perform in an open ebook assessment. Low performing students take advantage of the open ebook policy of the assessment and employ a strategy of searching for information during the assessment. Also compared to performance, the prediction of overall engagement has a higher accuracy, and therefore could be more appropriate for identifying intervention candidates as an early-warning intervention system.

Metaheuristics Method for Classification and Prediction of Student Performance Using Machine Learning Predictors

Over the last few decades, there has been a gradual deterioration in higher education in all three areas: the academic setting (both staff and students), as well as research and development output (including graduates). All colleges and universities are essentially focused on improving management decision-making and educating pupils. High-quality higher education can be obtained through a variety of methods. One method is to accurately forecast pupils’ achievement in their chosen educational context. There are numerous prediction models from which to pick. While it is unclear whether there are any markers that can predict whether a kid will be an academic genius, a dropout, or an average performer, the researcher reports student achievement. This article presents a metaheuristics and machine learning-based method for the classification and prediction of student performance. Firstly, features are selected using a relief algorithm. Machine learning classifiers such as BPNN, RF, and NB are used to classify student academic performance data. BPNN is having better accuracy for classification and prediction of student academic performance.

The role of demographic and academic features in a student performance prediction

Educational Data Mining is widely used for predicting student's performance. It’s a challenging task because a plethora of features related to demographics, personality traits, socio-economic, and environmental may affect students' performance. Such varying features may depend on the level of study, program offered, nature of subject, and geographical location. This study attempted to predict the final semester’s results of students studying Doctor of Veterinary Medicine (DVM) based on their pre-admission academic achievements, demographics, and first semester performance. The imbalanced data led to non-generic prediction models, so it was addressed through synthetic minority oversampling technique. Among five prediction models, the Support Vector Machine led the best with 92% accuracy. The decision tree model identified key features affecting students’ performance. The analysis led to the conclusion that marks obtained in Biology, Islamiat, and Urdu at Matric and English at Intermediate level affected the students’ performance in their final semester. The findings provide useful information to predict students’ performance and guidelines for academic institutes’ management regarding improving students’ achievement. It is speculated that adoption of digital transformation may help reduce difficulty faced in data collection and analysis.

Multi-view hypergraph neural networks for student academic performance prediction

Academic performance prediction is a fundamental and hot issue in educational data mining (EDM). Recently, researchers have proposed a series of effective machine learning (ML) based classification strategies to predict students’ academic performance. However, prior arts are typically concerned about individual models but neglect the association among students, which might considerably have an effect on the integrity of the academic performance-related representations. Meanwhile, students’ multi-viewing behavior contains complex relations among students. Therefore, we propose a Multi-View Hypergraph Neural Network (MVHGNN) for predicting students’ academic performance. MVHGNN uses hypergraphs to construct high-order relations among students. The semantic information implied by multiple behaviors is consolidated through meta-paths. Further, a Cascade Attention Transformer (CAT) module is introduced to mine the weight of different behaviors by the self-attention mechanism. Our method is evaluated on real campus student behavioral datasets. The experimental results demonstrate that our method outperforms the state-of-the-art ones.