Predicting Student Performance Using Clickstream Data and Machine Learning

Liu, Yutong; Fan, Si; Xu, Shuxiang; Sajjanhar, Atul; Yeom, Soonja; Wei, Yuchen

doi:10.3390/educsci13010017

Cited by 21 publications

(7 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, based on all three performance measures and their rather low standard deviation (computed from the 10-model accuracy), it can be said that the deep learning model can robustly predict the final score of learners when they complete 30% to 70% of their solutions. Our findings are consistent with those reported by Liu et al [34], Hajra et al [35], and Baranyi et al [36] in that deep neural networks could outperform traditional machine learning techniques in prediction tasks of learner performance. While like the work reported by Chen and Cui [37] and Okubo et al [38], we found that longer sequences of learner's actions could improve the prediction power of deep learning models, our results show that they may not necessarily be able to provide the optimal predictive performance.…”

Section: Performance Of Models Using Cross-validation: Validation Phasesupporting

confidence: 93%

Modeling Learners to Early Predict Their Performance in Educational Computer Games

et al. 2023

View full text Add to dashboard Cite

Data mining approaches have proven to be successful in improving learners´interaction with educational computer games. Despite the potential of predictive modelling in providing timely adaptive learning and gameplay experience, there is a lack of research on the early prediction of learners' performance in educational games. In this research, we propose an early predictive modelling approach, called GameEPM, to estimate learners' final scores in an educational game for promoting computational thinking. Specifically, the GameEPM approach models the sequence of learners' actions and then uses a limited sequence of the actions to predict the final score of the game for each learner. The findings from our initial trials show that our approach can accurately and robustly estimate the learners' performance at the early stages of the game. Using less than 50% of learners' action sequences, the cross-validated deep learning model achieves a squared correlation higher than 0.8 with a relative error of less than 8%, outperforming a range of regression models like linear regression, random forest, neural networks, and support vector machines. An additional experiment showed that the validated deep learning model can also achieve high performance while tested on an independent game dataset, showing its applicability and robustness in real-world cases. Comparing the results with traditional machine learning methods revealed that, in the validation and application phases, up to 0.30 and 0.35 R 2 gain is achieved in favor of the deep learning model, respectively. Finally, we found that while the lengths of action sequences influence the predictive power of the traditional machine learning methods, this effect is not substantial in the deep learning model.

show abstract

Section: Performance Of Models Using Cross-validation: Validation Phasesupporting

confidence: 93%

Modeling Learners to Early Predict Their Performance in Educational Computer Games

et al. 2023

View full text Add to dashboard Cite

show abstract

“…This means that the model depends on the information available at that time to predict the student performance after a specific length of time, such as at the start of a course or semester. The CNN-LSTM architectures Aljaloud et al (2022); Chen et al (2022); Duru et al (2021); Li et al (2022); Liu et al (2023); Xiong et al (2022) have achieved a high accuracy of more than 70.25% and up to 91%, and on average 85.89%, except in Song et al (2020) which has achieved an accuracy of about 61% (See Figure 7).…”

Section: Hybrid DL Modelsmentioning

confidence: 99%

“…To predict student's success on the final exam, Sikder et al (2022) A study by Liu et al (2023) examined how clickstream data can be used to predict student performance. The study utilized the most important indicators of how well students would perform from the OULA dataset with weekly and monthly time intervals; these indicators included clicks on the homepage, related sites, quizzes, and content.…”

Section: Hybrid DL Techniquesmentioning

confidence: 99%

Deep Learning Techniques for Predicting Student’s Academic Performance on Virtual Learning Environments: A Review

Alnasyan,

Basheri,

Alassafi

2024

Preprint

View full text Add to dashboard Cite

With advances in Artificial Intelligence (AI) and the increasing volume of online educational data, Deep Learning techniques have played a critical role in predicting student’s academic performance. Recent developments have assisted instructors in determining the strengths and weaknesses of student’s academic achievement. This understanding will benefit from adopting the necessary interventions to assist students in improving their performance, helping at-risk students, and preventing dropout rates. In this review, 46 studies between 2019 and 2023 that apply one or more Deep Learning (DL) techniques, either alone or in combination with Machine Learning (ML) or Ensemble Learning techniques, have been reviewed and analyzed. Moreover, the review has examined utilizing datasets from public (MOOCs), private (LMSs), and other platforms. Four categories were used to group the features: demographic, previous and current academic performance, and learning behavior/activity features. Therefore, the analysis has demonstrated that the DNNs and CNN-LSTM models were the most commonly used techniques. Moreover, it has been noted that the studies that have used DL techniques such as CNNs, DNNs, and LSTMs, performed well by achieving high prediction accuracy above 90%; other studies achieved accuracy ranging between 60% and 90%. For datasets used within the reviewed studies, even though 44% of the studies have used LMSs datasets, it is found that OULAD was the most used dataset from MOOCs. For the grouped features, the results of the analysis indicate that the best features for prediction are the learning behavior and activity features, which outperform other feature categories.

show abstract

“…When all training examples in the terminal/leaf node t within the same class, then the stopping criterion is said to be reached (Junshuai, 2019) Every node matches a characteristic, while the branches link with an array of values. All nodes are labelled with the attributes they test, and every branch is labelled with its corresponding values (Liu et al, 2023). The range of values is mutually exclusive and complete.…”

Section: Decision Treesmentioning

confidence: 99%

Determining Student Demographic Attributes Influencing Performance Using Binary Classification in KDP Model

Issah

Appiahene

Appiah

et al. 2023

Preprint

View full text Add to dashboard Cite

Machine learning (ML) is one way that can help decipher the intricate relationship between students' data and their performance. When implemented correctly in learning environments, machine learning will improve knowledge of fundamental processes by simplifying the identification, extraction, and evaluation of underlying factors that affect student learning and levels of achievement. This study employed the experimental research approach using binary classification techniques based on the six-step Knowledge Discovery Process (KDP) model. Five classifiers were used within the Rapid Miner's 9.10.010 educational environment as both experimental and analytical tool. The dataset comprised of 2334 records, 17 attributes with one class variable (students’ semester average score) inclusive. Twenty different tests were conducted. The experiments' results were evaluated using 10-fold cross-validation and ratio split validation with bootstrap sampling. The Random Forest algorithm (RF), Rule Induction methods (RI), Naive Bayes (NB), Logistic Regression (LR) and Deep Learning (DL) algorithms were used in the experiment. The experimental results demonstrated that the RF method outperforms the other four techniques in all six-evaluation metrics that were employed for the selection process with the accuracy being 93.96%. According to the RF classifier model, the mother's and father's education levels of students are two recognized demographic factors per this study that significantly influence pre-tertiary students’ academic achievement. This study has significantly reduced the gap in practical knowledge observed in the literature by introducing an intervention scheme for respective student's requiring intensive or minimal academic interventions in its prediction procedure.

show abstract

Predicting Student Performance Using Clickstream Data and Machine Learning

Cited by 21 publications

References 54 publications

Modeling Learners to Early Predict Their Performance in Educational Computer Games

Modeling Learners to Early Predict Their Performance in Educational Computer Games

Deep Learning Techniques for Predicting Student’s Academic Performance on Virtual Learning Environments: A Review

Determining Student Demographic Attributes Influencing Performance Using Binary Classification in KDP Model

Contact Info

Product

Resources

About