An overview and comparison of supervised data mining techniques for student exam performance prediction

Tomašević, Nikola; Gvozdenovic, Nikola; Vraneš, Sanja

doi:10.1016/j.compedu.2019.103676

Cited by 273 publications

(197 citation statements)

References 10 publications

Supporting

Mentioning

188

Contrasting

Unclassified

Order By: Relevance

“…These include linear and radial basis function kernel support vector machines (L-SVM and R-SVM), Gaussian processes (GP), Decision Tree (DT), Random Forest (RF), Neural Network (NN), AdaBoost (ADB), and Naive Bayes (NB). These classification methods are selected due to their popularity—the fact that they have been successfully used by many researchers in EDM research—and high performance compared to traditional methods (e.g., [ 36 , 44 ]). The classification methods with different numbers of classes are then compared by means of four different evaluation measures, namely accuracy, F1-score, precision, and recall.…”

Section: Methodsmentioning

confidence: 99%

“…Classification is a frequently used data mining method in education context, assigning an object to a class. In other words, classification is a specific case of prediction where a classifier—which uses training data to produce a classification model—predicts a class (label) or a discrete value [ 42 , 43 , 44 ]. Classification methods have been widely used in education to classify students according to their motivation, knowledge, and behavior (e.g., [ 45 ]).…”

Section: Previous Researchmentioning

confidence: 99%

See 1 more Smart Citation

Mining Educational Data to Predict Students’ Performance through Procrastination Behavior

Hooshyar

Pedaste

Yang

2019

Entropy

View full text Add to dashboard Cite

A significant amount of research has indicated that students’ procrastination tendencies are an important factor influencing the performance of students in online learning. It is, therefore, vital for educators to be aware of the presence of such behavior trends as students with lower procrastination tendencies usually achieve better than those with higher procrastination. In the present study, we propose a novel algorithm—using student’s assignment submission behavior—to predict the performance of students with learning difficulties through procrastination behavior (called PPP). Unlike many existing works, PPP not only considers late or non-submissions, but also investigates students’ behavioral patterns before the due date of assignments. PPP firstly builds feature vectors representing the submission behavior of students for each assignment, then applies a clustering method to the feature vectors for labelling students as a procrastinator, procrastination candidate, or non-procrastinator, and finally employs and compares several classification methods to best classify students. To evaluate the effectiveness of PPP, we use a course including 242 students from the University of Tartu in Estonia. The results reveal that PPP could successfully predict students’ performance through their procrastination behaviors with an accuracy of 96%. Linear support vector machine appears to be the best classifier among others in terms of continuous features, and neural network in categorical features, where categorical features tend to perform slightly better than continuous. Finally, we found that the predictive power of all classification methods is lowered by an increment in class numbers formed by clustering.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Previous Researchmentioning

confidence: 99%

Mining Educational Data to Predict Students’ Performance through Procrastination Behavior

Hooshyar

Pedaste

Yang

2019

Entropy

View full text Add to dashboard Cite

show abstract

“…Using a wide range of methods enables researchers to triangulate their findings and capitalise on the strength of each method (Veletsianos et al ., 2015). Tomasevic, Gvozdenovic, and Vranes (2020) provided a comprehensive analysis and comparison of the state‐of‐the‐art supervised machine learning techniques applied for the prediction of the student exam performance. A few researchers adopted classification algorithms to classify messages according to their relevance, course aspects or sentiment (positive, negative or neutral) (Brinton et al ., 2014; Bakharia, 2016).…”

Section: Literature Reviewmentioning

confidence: 99%

Understanding the focal points and sentiment of learners in MOOC reviews: A machine learning and SC‐LIWC‐based approach

Geng¹,

Niu²,

Feng³

et al. 2020

Brit J Educational Tech

View full text Add to dashboard Cite

Despite the popularity of massive open online courses (MOOCs), only a small portion of the course participants successfully complete the course. The low completion rate can be partially attributed to the mismatch between the participants' expectations and value delivered by the courses. Therefore, this study leverages MOOC reviews to investigate the focal point and sentiment of the learners by combining machine learning techniques and statistical analysis. Several text mining methods (ie, simplified Chinese‐linguistic inquiry and word count dictionary, word embeddings, and bidirectional long short‐term memory model) are combined to automatically extract the emotional and cognitive aspects, review focal point, and sentiment from the learner discourse. Multiple linear regression (MLR) analysis is performed to examine the relationships between the learner sentiment and the extracted content features. Using a set of real data from NetEase online open courses, our results reveal that the MOOC reviews mostly pertain to teaching and platform rather than the course content. Furthermore, the social process and personal concerns appear more frequently in the learner discourse. Overall, the learners exhibit positive attitudes towards teaching and platform and negative attitudes towards issues related to the course content. This study contributes to the literature regarding the MOOC research methodologies and provides a deeper understanding of the learner discourse behaviour in MOOCs.

show abstract

“…Results indicated that this deep learning approach outperformed support vector machine and logistic regression by 4.3% and 8.6% respectively. Here are the recommended state-of-the-art articles [19], [20] for readers who are interested in the overview of algorithms for students' performance prediction.…”

Section: Introductionmentioning

confidence: 99%

“…Existing works [14]- [18] possessed a common idea of analyzing the optimal feature vector from the dataset. Taking the review articles [19], [20] into account, to the best of our knowledge, there has no consideration on the prediction of students' performance under shadow education environment, that is school tutoring and family tutoring. On the other hand, the machine learning algorithms were mainly shallow learning approach because there is usually small data volume in education datasets.…”

Section: Introductionmentioning

confidence: 99%

Predicting Students’ Performance With School and Family Tutoring Using Generative Adversarial Network-Based Deep Support Vector Machine

et al. 2020

View full text Add to dashboard Cite

It has been witnessed that supportive learning has played a crucial role in educational quality enhancement. School and family tutoring offer personalized help and provide positive feedback on students' learning. Predicting students' performance is of much interest which reflects their understanding on the subjects. Particularly it is desired students to manage well in fundamental knowledge in order to build a strong foundation for post-secondary studies and career. In this paper, improved conditional generative adversarial network based deep support vector machine (ICGAN-DSVM) algorithm has been proposed to predict students' performance under supportive learning via school and family tutoring. Owning to the nature of the students' academic dataset is generally low sample size. ICGAN-DSVM offers dual benefits for the nature of low sample size in students' academic dataset in which ICGAN increases the data volume whereas DSVM enhances the prediction accuracy with deep learning architecture. Results with 10-fold cross-validation show that the proposed ICGAN-DSVM yields specificity, sensitivity and area under the receiver operating characteristic curve (AUC) of 0.968, 0.971 and 0.954 respectively. Results also suggest that incorporating both school and family tutoring into the prediction model could further improve the performance compared with only school tutoring and only family tutoring. To show the necessity of ICGAN and DSVM, comparison has been made between ICGAN and traditional conditional generative adversarial network (CGAN). Also, the proposed kernel design via heuristic based multiple kernel learning (MKL) is compared with typical kernels including linear, radial basis function (RBF), polynomial and sigmoid. The prediction of student's performance with and without GAN is presented which is followed by comparison with DSVM and with traditional SVM. The proposed ICGAN-DSVM outperforms related works by 8-29% in terms of performance indicators specificity, sensitivity and AUC.

show abstract

An overview and comparison of supervised data mining techniques for student exam performance prediction

Cited by 273 publications

References 10 publications

Mining Educational Data to Predict Students’ Performance through Procrastination Behavior

Mining Educational Data to Predict Students’ Performance through Procrastination Behavior

Understanding the focal points and sentiment of learners in MOOC reviews: A machine learning and SC‐LIWC‐based approach

Predicting Students’ Performance With School and Family Tutoring Using Generative Adversarial Network-Based Deep Support Vector Machine

Contact Info

Product

Resources

About