Predicting student performance in interactive online question pools using mouse interaction features

Student performance prediction is critical to online education. It can benefit many downstream tasks on online learning platforms, such as estimating dropout rates, facilitating strategic intervention, and enabling adaptive online learning. Interactive online question pools provide students with interesting interactive questions to practice their knowledge in online education. However, little research has been done on student performance prediction in interactive online question pools. Existing work on student performance prediction targets at online learning platforms with predefined course curriculum and accurate knowledge labels like MOOC platforms, but they are not able to fully model knowledge evolution of students in interactive online question pools. In this paper, we propose a novel approach using Graph Neural Networks (GNNs) to achieve better student performance prediction in interactive online question pools. Specifically, we model the relationship between students and questions using student interactions to construct the student-interaction-question network and further present a new GNN model, called R^2GCN, which intrinsically works for the heterogeneous networks, to achieve generalizable student performance prediction in interactive online question pools. We evaluate the effectiveness of our approach on a real-world dataset consisting of 104,113 mouse trajectories generated in the problem-solving process of over 4000 students on 1631 questions. The experiment results show that our approach can achieve a much higher accuracy of student performance prediction than both traditional machine learning approaches and GNN models.

Advances in Information and Communications Technology (ICT) have increased the growth of Massive open online courses (MOOCs) applied in distance learning environments. Various tools have been utilized to deliver interactive content including pictures, figures, and videos that can motivate the learners to build new cognitive skills. High ranking universities have adopted MOOCs as an efficient dashboard platform where learners from around the world can participate in such courses. The students learning progress is evaluated by using set computer-marked assessments. In particular, the computer gives immediate feedback to the student once he or she completes the online assessmentsThe researchers claim that student success rate in an online course can be related to their performance at the previous session in addition to the level of engagement. Insufficient attention has been paid by literature to evaluate whether student performance and engagement in the prior assessments could affect student achievement in the next assessmentsIn 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.

Machine learning can be beneficial to numerous fields, and of which is education. A particular area, which is predicting student performance, is selected in this paper to be reviewed. The objective of this paper is to find out what predictors can be used to predict student performance, what performances of students should be predicted, and what algorithms can be used for predicting student performance and which one has the best accuracy. To achieve those objectives, a systematic literature review has been done. In this research, it is found that there are various student features that can be used as predictors, student performance indicators that can be predicted with machine learning, and there are also a variety of machine learning algorithms that can be used in predicting student performance. Regarding the machine learning algorithm with the best accuracy/performance, the results differ from one research with the other. It is also found that increasing the number of predictors used and implementing techniques such as feature selection and data mining can improve accuracy of the prediction. We conclude that in predicting student performance, there are various predictors predicted student performance indicator, and machine learning algorithms that can be applied, as well as results regarding the most accurate machine learning algorithm differ.

The aim of this study is to undertake an empirical inquiry and comparison of the effectiveness of various classifiers with ensembles classifiers in the prediction of student academic performance. A single classifier algorithm will be compared against the performance and efficiency of ensemble classifiers. Reducing student attrition is a major problem for educational institutions all over the world. The search for solutions to increase student retention and graduation rates continues for educators. This is only possible if at-risk students are identified and intervened with as soon as possible. However, the majority of regularly used prediction models are inefficient and inaccurate as a result of inherent classifier limitations and the inclusion of insignificant inputs in their calculations. The majority of data mining and machine learning researcher focused on developing an algorithm that can extract useful information from massive amounts of data after being processed by a computer. The most difficult problem in predictive modelling is identifying the most effective prediction algorithms that are also accurate enough to be useful. Therefore, a multi-level homogeneous ensemble predictive (MLHoEP) model is designed, which uses the different techniques of data mining like feature selection, ensemble learning techniques like boosting and bagging. Seven distinct machine learning algorithms were used on this model to predict and analyse the academic performance of the students. The performance of the classification algorithms in terms of prediction was evaluated using k-fold cross-validation. The study contributes to the body of knowledge by suggesting the development of homogeneous classifiers that may be used to accurately predict students’ academic success. It also proposes the construction of homogeneous classifiers, which may be deployed for accurate student performance prediction, in order to provide a better explanation for the poor performance prediction. As a result of this research, it has been demonstrated that the technique of applying homogeneous ensemble approaches is incredibly efficient and accurate in terms of predicting student performance and assisting in identifying students, who are in danger of dropping out of school. The study compared the accuracy and efficiency of single classifiers to ensembles of classifiers in terms of performance. It was discovered in the research that a homogeneous model with excellent accuracy and efficiency might be developed for anticipating student performance. These key problems have been successfully addressed by the findings of this research study: Which characteristics of students are the most effective predictors of academic performance? How accurate are approaches such as bagging and boosting ensembles for predicting student academic performance? The approach offered in this study will aid educational administrators and policymakers in designing new policies and curriculum-linked to student retention in higher education. This research can also aid in the identification of students who are at risk of dropping out of school early, providing for timely intervention and support. Prospective research will examine the creation and implementation of an automated prediction system known as the students’ academic performance forecast framework, which will collect data from students via online submission and produce a prediction result for their academic performance.KeywordsEducational data miningEnsemble learningMultilayer perceptronRandom forestNaïve BayesCorrelation attribute evaluationInformation gainGain ratio

This study evaluated online and traditional learning for effectiveness and student satisfaction. 500 university students evaluated both learning methods. Data was quantified. Age, gender, and major were collected for diversity. Two questionnaires assessed student satisfaction and performance with online learning platforms and traditional classrooms. Likert-scale items rated satisfaction and efficacy. Online and traditional classrooms had interesting variances in student enjoyment and efficacy. Students liked online learning. Most students said online and traditional classrooms were beneficial. Online learning platforms were better at facilitating self-paced learning, tailored instruction, and a wide selection of learning materials. The findings can help educators and policymakers create and implement online learning platforms. The study also emphasizes the importance of student preferences and needs when constructing instructional tactics and the potential benefits of blended learning approaches that combine both learning modalities.

<p class="MsoNormal" style="text-align: justify;"><span style="font-family: Times New Roman;">This paper explores machine learning approaches to predicting student performance using artificial neural networks. By employing educational data mining and predictive modeling techniques, accurate predictions of student outcomes were achieved. The results indicate that artificial neural networks exhibit high accuracy and reliability in forecasting student academic performance. Through comprehensive analysis and empirical testing, this approach significantly enhances the effectiveness of student performance predictions. Future research directions may include further optimization of the model's algorithms and expansion of the data sample size to improve prediction accuracy and applicability. The method demonstrated exceptional performance in predicting student outcomes, offering high accuracy and efficacy. By mining and analyzing extensive educational data, a predictive model was established and validated through experiments. We introduce a novel predictive model to the field of education, providing robust support for student learning and educational decision-making. Future enhancements can optimize the model, increase prediction precision, and expand application fields to better serve the development of educational endeavors.</span></p>

Educational data mining (EDM) is a strategic technique for exploring data in educational environments to gain a deeper understanding of education. One of the goals of EDM is to predict things related to students in the future which can be done using a machine learning approach. In this paper, a regression model is developed to predict student performance in the first semester and the waiting period for graduate employment using machine learning approach based on informatics management (MI) and non-informatics management (non-MI) student data. Four regression models are compared for predicting student performance in the first semester and waiting period for graduate employment, including support vector regression (SVR), random forest regression (RFR), AdaBoost regression (ABR), and XGBoost regression. Based on the experiment, prediction of students' performance in the first semester, the highest R2 result produced by SVR model by value of 0.58 for MI and by RFR by value of 0.34 for non-MI. While, waiting period for graduate employment prediction, the highest R2 result produced by AdaBoost regression by value of 0.44 for MI and SVR by value of 0.39 for non-MI.

Student performance modelling is one of the challenging and popular research topics in educational data mining (EDM). Multiple factors influence the performance in non-linear ways; thus making this field more attractive to the researchers. The widespread availability of e ducational datasets further catalyse this interestingness, especially in online learning. Although several EDM surveys are available in the literature, we could find only a few specific surveys on student performance analysis and prediction. These specific surveys are limited in nature and primarily focus on studies that try to identify possible predictor or model student performance. However, the previous works do not address the temporal aspect of prediction. Moreover, we could not find any such specific survey which focuses only on classroom-based education. In this paper, we present a systematic review of EDM studies on student performance in classroom learning. It focuses on identifying the predictors, methods used for such identification, time and aim of prediction. It is significantly the first systematic survey of EDM studies that consider only classroom learning and focuses on the temporal aspect as well. This paper presents a review of 140 studies in this area. The meta-analysis indicates that the researchers achieve significant prediction efficiency during the tenure of the course. However, performance prediction before course commencement needs special attention.

Prediction of student performance is one of the most important subjects of educational data mining. Artificial neural networks are seen to be an effective tool in predicting student performance in e-learning environments. In the studies carried out with artificial neural networks, performance predictions based on student scores are generally made, but students’ use of learning management system is not focused. In this study, performances of 3518 university students, who studying and actively participating in a learning management system, were tried to be predicted by artificial neural networks in terms of gender, content score, time spent on the content, number of entries to content, homework score, number of attendance to live sessions, total time spent in live sessions, number of attendance to archived courses and total time spent in archived courses variables. Since it is difficult to interpret how much input variables in artificial neural networks contribute to predicting output variables, these networks are called black boxes. Also, in this study the amount of contribution of input variables on the prediction of output variable was also examined. The artificial neural network created as a result of the study makes a prediction with an accuracy of 80.47%. Finally, it was found that the variables of number of attendance to the live classes, the number of attendance to archived courses and the time spent in the content contributed most to the prediction of the output variable.

Predicting student performance is crucial for both preventing failure and enabling personalized teaching-and-learning strategies. The digitalization of educational institutions has led to the collection of extensive student learning data over the years. Current research primarily focuses on short-term data, e.g. a single year or semester. In contrast, long-term data has the potential to offer a deeper insight into student behavior, thereby increasing the accuracy of predictions. However, the direct application of long-term data in prediction models assumes consistent data distributions over time. In the real world, evolutions in course content and structure can lead to variations in feature spaces (heterogeneity) and distribution shifts across different academic years, compromising the effectiveness of prediction models. To address these challenges, we introduce the Learning Ability Self-Adaptive Algorithm (LASA), which can adapt to the evolving feature spaces and distributions encountered in long-term data. LASA comprises two primary components: Learning Ability Modeling (LAM) and Long-term Distribution Alignment (LTDA). LAM assumes that students’ responses to exercises are samples from distributions that are parameterized by their learning abilities. It then estimates these parameters from the heterogeneous student exercise response data, thereby creating a new homogeneous feature space to counteract the heterogeneity present in long-term data. Subsequently, LTDA employs multiple asymmetric transformations to align distributions of these new features across different years, thus mitigating the impact of distribution shifts on the model’s performance. With these steps, LASA can generate well-aligned features with meaningful semantics. Furthermore, we propose an interpretable prediction framework including three components, i.e. LASA, a base classifier for outcome predictions, and Shapley Additive Explanations (SHAP) for elucidating the impact of specific features on student performance. Our exploration of long-term student data covers an eight-year period (2016-2023) from a face-to-face course at Tsinghua University. Comprehensive experiments demonstrate that leveraging long-term data significantly enhances prediction accuracy compared to short-term data, with LASA achieving up to a 7.9% increase. Moreover, when employing long-term data, LASA outperforms state-of-the-art models, ProbSAP and SFERNN, by an average accuracy improvement of 6.8% and 6.4%, respectively. We also present interpretable insights for pedagogical interventions based on a quantitative analysis of feature impacts on student performance. To the best of our knowledge, this study is the first to investigate student performance prediction in long-term data scenarios, addressing a significant gap in the literature.

Higher educational institutions (HEIs) are striving to improve their student's performance. Classification of students to predict student's performance could be useful in identifying bad performers or late completers to improve at an early stage by forecasting their final outcome. In this study, three student's performance prediction models were investigated. J48 decision tree algorithm was used for the study. When the performance of these models was evaluated, it was found that the third prediction model provided better performance compared to the other models. Also, there was variation in the course-taking patterns of students and contextual attribute course difficulty depending on their completion time. This demonstrates the significance of students course-taking patterns on performance and time-to-degree. The most significant finding is that unlike easy course delivering high GPAs interestingly some very difficult courses too lead to optimum time and GPA which could be attributed to other hidden factors which need to be investigated.

Increasing student involvement in classes has always been a challenge for teachers and school managers. In online learning, some interactivity mechanisms like quizzes are increasingly used to engage students during classes and tasks. However, there is a high demand for tools that evaluate the efficiency of these mechanisms. In order to distinguish between high and low levels of engagement in tasks, it is possible to monitor brain activity through functional near-infrared spectroscopy (fNIRS). The main advantages of this technique are portability, low cost, and a comfortable way for students to concentrate and perform their tasks. This setup provides more natural conditions for the experiments if compared to the other acquisition tools. In this study, we investigated levels of task involvement through the identification of correct and wrong answers of typical quizzes used in virtual environments. We collected data from the prefrontal cortex region (PFC) of 18 students while watching a video lecture. This data was modeled with supervised learning algorithms. We used random forests and penalized logistic regression to classify correct answers as a function of oxyhemoglobin and deoxyhemoglobin concentration. These models identify which regions best predict student performance. The random forest and penalized logistic regression (GLMNET with LASSO) obtained, respectively, 0.67 and 0.65 area of the ROC curve. Both models indicate that channels F4-F6 and AF3-AFz are the most relevant for the prediction. The statistical significance of these models was confirmed through cross-validation (leave-one-subject-out) and a permutation test. This methodology can be useful to better understand the teaching and learning processes in a video lecture and also provide improvements in the methodologies used in order to better adapt the presentation content.

Aim/Purpose: Drawing on transactional distance theory (TDT) and collaborative learning, this research proposes a research model to examine the role of collaborative learning during the COVID-19 pandemic. It investigates the potential antecedents that influence students’ academic achievements, autonomy, and satisfaction with online learning platforms. Background: The coronavirus (COVID-19) epidemic devastating the world has shaken the global educational system; such a transformation compelled all educational institutes to utilize online learning platforms. Malaysian higher educational institutions were greatly concerned by this disease and faced considerable transformations that affected higher education learners. Additionally, the campus closure and movement regulations impacted traditional education. Thus, the Malaysian Government ordered students at higher education institutions to return to their hometowns and continue their studies through online learning. Therefore, online learning was the most reasonable alternative to resume the learning process. Furthermore, in the educational world, collaborative learning is pivotal to forming students’ interpersonal skills. Collaborative learning practice is working in pairs or small groups to attain the learning objectives collaboratively. Collaborative learning refers to the process of acquiring knowledge in a collaborative setting as opposed to alone. Since the instructor and students are in separate locations, it is challenging for the teacher to facilitate collaborative learning. Methodology: This study utilized a quantitative method; purposive sampling was implemented, and the data were collected from 260 university students, both undergraduate and postgraduate, as long as they were affected by the COVID-19 pandemic in Malaysia. The questionnaire for this research was designed to fit the research hypothesis. The items of the questionnaire have been adapted to certify the content’s validity. The collected data were analyzed using Smart PLS software, which has been utilized as an essential data analysis tool. Contribution: This research contributes to: (1) a better understanding of the importance of communication and connection among students-students and teachers in online learning environments, as the results suggest that the more communication between students, teachers, and the environment itself, the greater the academic achievements, learners’ autonomy, and satisfaction; and (2) the role of both collaborative learning and TDT on learners’ academic achievements, autonomy, and satisfaction. Findings: This study advances by incorporating TDT and collaborative learning theories. This research model illustrates six main factors in online learning platforms that enhance students’ academic achievements, autonomy, and satisfaction through collaborative learning. The results showed a strong association between TDT and collaborative learning regarding the online learning platforms’ utilization for improving academic achievements, learners’ autonomy, and satisfaction. Recommendations for Practitioners: This model provided exceptional support to students during this sudden switch to online alternatives and helped them cope with the considerable challenges they faced under the current circumstances. Moreover, this model provides a guideline for higher education teachers and administrators for coping with online learning platforms. Recommendation for Researchers: Drawing on the association between TDT and collaborative learning regarding the utilization of online learning platforms for improving academic achievements, learners’ autonomy, and learner satisfaction, the research result presents a road map for researchers in the field of online learning. Accordingly, researchers are encouraged to utilize these theories, as they can lead to improvements among online learners in higher education institutions. Impact on Society: This preliminary model, which was developed throughout this research, will be a great support to both researchers and instructors to be able to utilize and elaborate in accordance with the role of online platforms on students’ satisfaction, autonomy, and academic achievements. It is critical for higher education administrators to pay more attention to the nature of communication between students and student instructors, which has been shown to have a positive influence on their academic achievements, to implement online learning. Moreover, instructors and course developers must be trained and skilled to achieve online learning platform goals. Future Research: Future research could include more information about blended learning environments and their relationship to the technology acceptance model as an online learning model. Researchers may extend the model used in this study.

This study proposes a technically robust machine learning framework for predicting student academic performance, specifically targeting the final grade (G3), by leveraging the Portuguese student dataset. The approach incorporates comprehensive data preprocessing techniques, including categorical encoding, feature scaling, and dimensionality reduction via Principal Component Analysis (PCA), to enhance data quality and model performance. A Multi-Layer Perceptron Regressor (MLPRegressor) is employed to model the complex, non-linear relationships between academic, demographic, and behavioral input features and student outcomes. The system is deployed through a web-based interface developed using Flask, integrated with Gradio for interactive and real-time prediction capabilities. Additionally, an API layer is incorporated to support seamless integration with external platforms. This architecture supports data-driven educational interventions by enabling early identification of at-risk students and aiding institutions in implementing targeted academic support strategies. Index Terms: Student Performance Prediction, Machine Learning, MLP Regressor, Educational Data Mining, Academic Analytics

Vocational education increasingly adopts blended learning approaches, combining online and traditional instruction to enhance skill development and learning outcomes. As students engage in various digital activities, they generate large volumes of behavioral data that can be leveraged to predict academic performance and enable early intervention for at-risk learners. This research proposes a deep learning-based student performance prediction framework tailored to vocational education environments, utilizing multi-source behavioral data. Data were collected from 2000 vocational learners enrolled in a semester-long program. The framework utilizes multi-source behavioral data, including Learning Management System (LMS) activity logs, internet usage patterns, attendance records, assessments, and demographic information, to enhance predictive accuracy and support early intervention in vocational education. Data were preprocessed by handling missing values, data cleaning, and min-max normalization. Principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) were fused to extract dynamic behavioral features. The proposed model, the Seven-spot Ladybird Optimized Multi-Source Attention-based Gated Recurrent Units (SLO-MSAGRU) model, is applied to predict student performance in vocational education. Implemented in Python, the findings show that the SLO-MSAGRU approach performs better than multimodal baseline architectures, achieving superior results with accuracy, F1-score, recall, and precision ranging from 95% to 98%. These findings reveal that broader internet behavior patterns contribute more significantly to student performance prediction than platform-specific learning data. The framework offers a practical tool for educators to apply personalized learning strategies and timely interventions, thereby improving decision-making in vocational training environments.