Predicting Student Performance and Deficiency in Mastering Knowledge Points in MOOCs Using Multi-Task Learning

Qu, Shaojie; Li, Kan; Xu-ri, Zhang; Zhu, Kaihao

doi:10.3390/e21121216

Cited by 15 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In turn, our results show greater robustness than those obtained in [19] in which it was possible to obtain values of accuracy, precision, recall and F1 score of 87.44%, 52.84%, 50.68% and 51.73% respectively, to be applied in predicting students graduating on time. This affirmation can be sustained in the study of [29] where it is pointed out that these metrics reflect a high capacity of the classification model, because, the greater the recall, the greater the capacity of the model to recognize positive instances, the greater the Whatever the accuracy, the capacity of the model to distinguish instances will be reflected, finding the F1 score as the combination of the two metrics, in this sense, the higher the F1 score, the more solid the classification model will be. Validated the use of the SVM Quadratic algorithm in the predictive model of the satisfaction of university students, the classification model is evaluated by means of the receiver operating characteristic curve (ROC) technique, which allows us to visualize the balance between the rate of true positives (TPR) and the false negative rate (FNR).…”

Section: Figure 2 Algorithm Accuracy Validationmentioning

confidence: 69%

Quadratic vector support machine algorithm, applied to prediction of university student satisfaction

Chamorro-Atalaya

Morales-Romero

Meza-Chaupis

et al. 2022

IJEECS

View full text Add to dashboard Cite

This study aims to identify the most optimal supervised learning algorithm to be applied to the prediction of satisfaction of university students. In this study, the IBM SPSS - 25.0 software was used to test the reliability of the satisfaction questionnaire and the MATLAB R2021b software through the classification learner technique to determine the supervised learning algorithm. The experimental results determine a Cronbach's Alpha reliability of 0.979, in terms of the classification algorithm, it is validate d that the quadratic vector support machine (SVM) has better performance metrics, being correct in 97.8% (a ccuracy) in the predictions of satisfaction of university students, with a r ecall (sensitivity) of 96.5% and an F1 score of 0.968. Likewise, when eva luating the classification model by means of the receiver operating characteristic curve (ROC) technique, it is identified that for the three expected classes of satisfaction the value of the area under the curve (AUC) is equal to 1, in such sense the pred ictive model through the SVM Quadratic algorithm, has a high capacity to distinguish between the 3 classes ; i) d issatisfied, ii) s atisfied and iii) v ery satisfied of satisfaction of university students.

show abstract

Section: Figure 2 Algorithm Accuracy Validationmentioning

confidence: 69%

Quadratic vector support machine algorithm, applied to prediction of university student satisfaction

Chamorro-Atalaya

Morales-Romero

Meza-Chaupis

et al. 2022

IJEECS

View full text Add to dashboard Cite

show abstract

“…Due to the impact of the COVID-19 pandemic, e-learning has been widely used worldwide due to its high temporal and spatial flexibility, low knowledge acquisition threshold, and rich learning resources. However, in this mode, teachers cannot easily perceive the learning status of their learners 2 , and questions about the quality of e-learning have been raised. The study of learning performance prediction provides a basis for teachers to adjust their teaching methods for students who may have problems by predicting students’ performance on future exams, reducing the risk of students failing to pass the course, and ensuring the quality of e-learning.…”

Section: Introductionmentioning

confidence: 99%

Predicting students’ performance in e-learning using learning process and behaviour data

Qiu

Zhang

Sheng

et al. 2022

Sci Rep

View full text Add to dashboard Cite

E-learning is achieved by the deep integration of modern education and information technology, and plays an important role in promoting educational equity. With the continuous expansion of user groups and application areas, it has become increasingly important to effectively ensure the quality of e-learning. Currently, one of the methods to ensure the quality of e-learning is to use mutually independent e-learning behaviour data to build a learning performance predictor to achieve real-time supervision and feedback during the learning process. However, this method ignores the inherent correlation between e-learning behaviours. Therefore, we propose the behaviour classification-based e-learning performance (BCEP) prediction framework, which selects the features of e-learning behaviours, uses feature fusion with behaviour data according to the behaviour classification model to obtain the category feature values of each type of behaviour, and finally builds a learning performance predictor based on machine learning. In addition, because existing e-learning behaviour classification methods do not fully consider the process of learning, we also propose an online behaviour classification model based on the e-learning process called the process-behaviour classification (PBC) model. Experimental results with the Open University Learning Analytics Dataset (OULAD) show that the learning performance predictor based on the BCEP prediction framework has a good prediction effect, and the performance of the PBC model in learning performance prediction is better than traditional classification methods. We construct an e-learning performance predictor from a new perspective and provide a new solution for the quantitative evaluation of e-learning classification methods.

show abstract

“…Lee et al [33] where the authors point out that an accuracy greater than 90, it is possible to optimally predict the graduation of the students. This statement is supported by [34], in this study the authors state that in supervised learning the precision of the algorithm depends on the accuracy, for this reason it is important that this indicator provides us with optimal values. In relation to the evaluation of the performance indicators through the confusion matrix where an average sensitivity of 97.9%, a specificity of 99.1% and precision of 96.7% are observed, which validate the capacity of the weighted KNN algorithm to correctly predict the perception of university teaching performance.…”

Section: Resultsmentioning

confidence: 74%

Supervised learning through k-nearest neighbor, used in the prediction of university teaching performance

Chamorro-Atalaya

Alvarado-Bravo

Aldana-Trejo

et al. 2022

IJEECS

View full text Add to dashboard Cite

This study initially seeks to identify the most optimal supervised learning algorithm to be used in predicting the perception of teacher performance, and then to evaluate its performance indicators that validate its predictive capacity. For this, the Matlab R2021a software is used; the experimental results determine that the supervised learning algorithm K-Nearest Neighbor Weighted (Weighted KNN) will be correct in 98.10% in predicting the perception of teaching performance, this has been validated by carrying out two evaluations through its performance indicators obtained in the confusion matrix and the receiver operating characteristic (ROC) curve, in the first evaluation an average sensitivity of 97.9%, a specificity of 99.1%, an accuracy of 98.8% and a precision of 96.7% are observed, thus validating the ability of the Weighted KNN model to correctly predict the perception of teacher performance; while in the receiver operating characteristic (ROC) curve, values of the area under the curve (AUC) equal to 0.99 and 1 are obtained, with this it is possible to validate the capacity that the model will have to distinguish between the 4 classes of the perception of the university teaching performance.

show abstract

Predicting Student Performance and Deficiency in Mastering Knowledge Points in MOOCs Using Multi-Task Learning

Cited by 15 publications

References 36 publications

Quadratic vector support machine algorithm, applied to prediction of university student satisfaction

Quadratic vector support machine algorithm, applied to prediction of university student satisfaction

Predicting students’ performance in e-learning using learning process and behaviour data

Supervised learning through k-nearest neighbor, used in the prediction of university teaching performance

Contact Info

Product

Resources

About