Academic Performance Prediction Based on Multisource, Multifeature Behavioral Data

Zhao, Liang; Chen, Kun; Song, Jie; Zhu, Xiaoliang; Sun, Jianwen; Caulfield, Brian; Namee, Brian Mac

doi:10.1109/access.2020.3002791

Cited by 36 publications

(35 citation statements)

References 62 publications

(145 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…E-learning behaviour data can accurately describe the time and energy that students spend on a specific course, such as the frequency of access to course materials 22 and the frequency of online discussions 23 . Some studies also tried to use the combination of two indicators to complete learning prediction 24 but encountered problems related to increasing computational costs.…”

Section: Related Workmentioning

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

Section: Related Workmentioning

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

show abstract

“…Moreover, machine learning algorithms are also used to identify key factors that influence students' academic success in schools and explore the relationship between these key factors [21], [22]. For example, predicting student learning outcomes by combining various aspects of student life, namely student personality; behavior and learning styles as well as lifestyles such as sleep patterns, exercise patterns and others [23].…”

Section: Discussion Of the Findingsmentioning

confidence: 99%

Machine Learning Algorithm to Predict Student’s Performance: A Systematic Literature Review

Sandra¹,

Lumbangaol²,

Matsuo³

2021

TEM Journal

View full text Add to dashboard Cite

One of the ultimate goals of the learning process is the success of student learning. Using data and students' achievement with machine learning to predict the success of student learning will be a crucial contribution to everyone involved in determining appropriate strategies to help students perform. The selected 11 research articles were chosen using the inclusion criteria from 2753 articles from the IEEE Access and Science Direct database that was dated within 2019-2021 and 285 articles that were research articles. This study found that the classification machine learning algorithm was most often used in predicting the success of students' learning. Four algorithms that were used most often to predict the success of students' learning are ANN, Naïve Bayes, Logistic Regression, SVM and Decision Tree. Meanwhile, the data used in these research articles predominantly classified students' success in learning into two or three categories which are pass/fail; or fail/pass/excellent.

show abstract

“…In the analysis of behavior entropy, we firstly focus on the record of a learner’s behavior throughout the day (i.e., {t 1 , t 2 , ···, t n }). Subsequently, we divide one day into 48 time bins such that each bin spans 30 min [ 14 , 18 , 19 ]; therefore, every bin is encoded from 1 to 48 (i.e., t i ′∈ {1, 2, ···, 48}, where i denotes the i th time bin). Then, the time series {t 1 , t 2 , ···, t n } can be mapped into a discrete time sequence {t 1 ′, t 2 ′, ···, t n ′}.…”

Section: Methodsmentioning

confidence: 99%

MOOC Behavior Analysis and Academic Performance Prediction Based on Entropy

Zhu

Zhao

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

In recent years, massive open online courses (MOOCs) have received widespread attention owing to their flexibility and free access, which has attracted millions of online learners to participate in courses. With the wide application of MOOCs in educational institutions, a large amount of learners’ log data exist in the MOOCs platform, and this lays a solid data foundation for exploring learners’ online learning behaviors. Using data mining techniques to process these log data and then analyze the relationship between learner behavior and academic performance has become a hot topic of research. Firstly, this paper summarizes the commonly used predictive models in the relevant research fields. Based on the behavior log data of learners participating in 12 courses in MOOCs, an entropy-based indicator quantifying behavior change trends is proposed, which explores the relationships between behavior change trends and learners’ academic performance. Next, we build a set of behavioral features, which further analyze the relationships between behaviors and academic performance. The results demonstrate that entropy has a certain correlation with the corresponding behavior, which can effectively represent the change trends of behavior. Finally, to verify the effectiveness and importance of the predictive features, we choose four benchmark models to predict learners’ academic performance and compare them with the previous relevant research results. The results show that the proposed feature selection-based model can effectively identify the key features and obtain good prediction performance. Furthermore, our prediction results are better than the related studies in the performance prediction based on the same Xuetang MOOC platform, which demonstrates that the combination of the selected learner-related features (behavioral features + behavior entropy) can lead to a much better prediction performance.

show abstract

Academic Performance Prediction Based on Multisource, Multifeature Behavioral Data

Cited by 36 publications

References 62 publications

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

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

Machine Learning Algorithm to Predict Student’s Performance: A Systematic Literature Review

MOOC Behavior Analysis and Academic Performance Prediction Based on Entropy

Contact Info

Product

Resources

About