Using learning analytics to develop early-warning system for at-risk students

Akçapınar, Gökhan; Altun, Arif; Aşkar, Petek

doi:10.1186/s41239-019-0172-z

Cited by 100 publications

(105 citation statements)

References 15 publications

Supporting

Mentioning

100

Contrasting

Unclassified

Order By: Relevance

“…IG(S, a) = H(S)-H(S|a) (10) where, IG(S, a) is the dataset S information for the variable a for a random variable, H(S) is the entropy for the dataset before any adjustment and H(S | a) is the conditional entropy for the variable given a. Table 6 shows the important features that support the classification results arranged from the higher ratio to the lower.…”

Section: Results Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Egyptian Social Insurance Big Data Mining Using Supervised Learning Algorithms

Senousy¹,

Hanna²,

Shehab³

et al. 2019

RIA

View full text Add to dashboard Cite

Social insurance is an important way to defend individuals from the dangers of retirement, sickness, and financial despondency. However, the social insurance data of Egypt are extremely massive, diverse and complex, due to the intricate provisions in Egyptian laws on social insurance. This calls for an effective method to distinguish between the insured and the uninsured based on the big data. Therefore, this paper fully demonstrates the capability of supervised learning algorithms in predicting the insured and the uninsured based on some of the data on social insurance. The big dataset of Egyptian social insurance was preprocessed in details, including replacing the missing values with mean values, normalization, and removal of outliers and extreme values. Next, three supervised learning algorithms, namely, Naive Bayes, Decision Tree Algorithm, and CN2 Rule Induction, were applied to classify the Egyptians based on the preprocessed data. The results show that all three algorithms achieved highly accuracy classification results. The research provides a new way to mine useful information from the big data of social insurance.

show abstract

Section: Results Discussionmentioning

confidence: 99%

“…Akçapınar et al [10] the authors used learning analytics to develop an early warning system for at-risk students. They used in the implementation of their research experiment the Orange data mining tool.…”

Section: Introductionmentioning

confidence: 99%

Egyptian Social Insurance Big Data Mining Using Supervised Learning Algorithms

Senousy¹,

Hanna²,

Shehab³

et al. 2019

RIA

View full text Add to dashboard Cite

show abstract

“…Interventions at this stage can be effective in preventing students' possible failures. Studies demonstrate that the students' end-of-year performances can be predicted accurately from the first weeks of the course (Akçapınar, Altun, & Aşkar, 2019). It is fundamental to design and test interventions especially for students who are likely to fail the course in future studies.…”

Section: Discussionmentioning

confidence: 99%

“…The regression model that emerged as a result of the analysis shows that the interaction data reflecting the students' online learning behavior can markedly predict 70% of the variance in learning performance. Moreover, in another study, an early warning system is developed to estimate the academic performance of the at-risk students by using learning analytics data in a Computer Hardware course conducted through blended learning (Akçapınar, Altun, & Aşkar, 2019). As a result of the study in which different classification algorithms are put to work; It is revealed that the prediction models created based on the interaction data of the students can predict the students who are going to fail in the third week of the course.…”

Section: Online Learning Experiences In Terms Of Blended Learningmentioning

confidence: 99%

Analyzing the Relationship between Student’s Assignment Submission Behaviors and Course Achievement through Process Mining Analysis

Akçapınar¹,

Kokoç²

2020

Turkish Journal of Computer and Mathematics Education (TURCOMAT)

View full text Add to dashboard Cite

In this study, it is aimed to analyze the relationship between student's assignment submission behaviors and course achievement. For this purpose, the behaviors of 75 students' who enrolled in the Operating Systems and Applications course at a public university, submission an assignment through the Moodle learning management system given in the fourth week of the course is analyzed. Students who exhibit different assignment submission behaviors are also analyzed in terms of endof-term grades. During analyzing, the steps followed by the students while submitting their assignments are determined respectively, and students who display a similar pattern are divided into groups by means of cluster analysis. Moreover, using process mining analysis assignment submission processes of students in different groups are analyzed in detail. The analysis shows that students can be divided into three different groups based on their assignment submission behaviors. In terms of course achievement, it is observed that a significant portion of the students who submitted the assignments are successful in the course, while a significant portion of the students who did not submit the assignment failed. The findings will be guideway in determining the students who are likely to fail the course in the early weeks and in designing possible interferences for these students.

show abstract

“…The prediction of student academic performance helps in identifying weak students who will struggle with their studies. Science and IT majors are among the hardest at college level [1], [2]. Therefore, the management of computer and IT related institutions take essential steps to detect and correct the way for weak students.…”

Section: Introductionmentioning

confidence: 99%

RHEM: A Robust Hybrid Ensemble Model for Students’ Performance Assessment on Cloud Computing Course

Sakri¹,

Alluhaidan²

2020

IJACSA

View full text Add to dashboard Cite

Creating tools, such as a prediction model to assist students in a traditional or virtual setting, is an essential activity in today's educational climate. The early stage towards incorporating these predictive models using techniques of machine learning focused on predicting the achievement of students in terms of the grades obtained. The research aim is to propose a robust hybrid ensemble model (RHEM) that can warn at-risks students (on Cloud Computing course) of their likely outcomes at the early semester assessment. We hybridised four renowned single algorithms-Naïve Bayes, Multilayer Perceptron, k-Nearest Neighbours, and Decision Tablewith four well-established ensemble algorithms-Bagging, RandomSubSpace, MultiClassClassifier, and Rotation Forestwhich produced 16 new hybrid ensemble classifier models. Hence, we have thoroughly and rigorously built, trained, and tested 24 models all together. The experiment concluded that the Rotation Forest + MultiLayer Perceptron model was the best performing model based on the model evaluation in terms of Accuracy (91.70%), Precision (86.1%), F-Score rate (87.3%), and Receiver Operating Characteristics Area detection (98.6%). Our research will help students identify their likely final grades in terms of whether they are excellent, very good, good, pass, or fail, and, thus, transform their academic conduct to achieve higher grades in the final exam accordingly.

show abstract

Using learning analytics to develop early-warning system for at-risk students

Cited by 100 publications

References 15 publications

Egyptian Social Insurance Big Data Mining Using Supervised Learning Algorithms

Egyptian Social Insurance Big Data Mining Using Supervised Learning Algorithms

Analyzing the Relationship between Student’s Assignment Submission Behaviors and Course Achievement through Process Mining Analysis

RHEM: A Robust Hybrid Ensemble Model for Students’ Performance Assessment on Cloud Computing Course

Contact Info

Product

Resources

About