Dataset Information

Enhancing tertiary students' programming skills with an explainable Educational Data Mining approach.

ABSTRACT: Educational Data Mining (EDM) holds promise in uncovering insights from educational data to predict and enhance students' performance. This paper presents an advanced EDM system tailored for classifying and improving tertiary students' programming skills. Our approach emphasizes effective feature engineering, appropriate classification techniques, and the integration of Explainable Artificial Intelligence (XAI) to elucidate model decisions. Through rigorous experimentation, including an ablation study and evaluation of six machine learning algorithms, we introduce a novel ensemble method, Stacking-SRDA, which outperforms others in accuracy, precision, recall, f1-score, ROC curve, and McNemar test. Leveraging XAI tools, we provide insights into model interpretability. Additionally, we propose a system for identifying skill gaps in programming among weaker students, offering tailored recommendations for skill enhancement.

SUBMITTER: Islam MR

PROVIDER: S-EPMC11371252 | biostudies-literature | 2024

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Enhancing tertiary students' programming skills with an explainable Educational Data Mining approach.

Islam Md Rashedul MR Nitu Adiba Mahjabin AM Marjan Md Abu MA Uddin Md Palash MP Afjal Masud Ibn M Mamun Md Abdulla Al MAA

PloS one 20240903 9

Educational Data Mining (EDM) holds promise in uncovering insights from educational data to predict and enhance students' performance. This paper presents an advanced EDM system tailored for classifying and improving tertiary students' programming skills. Our approach emphasizes effective feature engineering, appropriate classification techniques, and the integration of Explainable Artificial Intelligence (XAI) to elucidate model decisions. Through rigorous experimentation, including an ablation ...[more]

PMID: 39226285

Similar Datasets

Project description:Current evidence indicates that undergraduate medical students display deficits in musculoskeletal physical examination skills (MPES). While various instructional methods are recommended for teaching clinical skills, effective methods for teaching MPES have not been established. This study compared the effectiveness of a multimodal teaching approach incorporating video-based learning, interactive small-group teaching, hands-on practicing, peer-assisted learning, formative assessment, and constructive feedback with traditional bedside teaching in developing undergraduate orthopedic MPES. Participants were 151 fifth-year medical students divided into two groups. One group received multimodal teaching, and the other received traditional bedside teaching. In both groups, the participants learned how to physically examine the knee and shoulder. The primary outcome was objective structured clinical examination (OSCE) scores, while the secondary outcomes included teaching sessions' total durations, facilitator's demonstration time, participants' practice time, and proportion of students with passing checklist scores and global ratings-based assessments for the two teaching approaches. The multimodal teaching group had significantly higher OSCE scores (checklist scores, global ratings, and passing rates; p = 0.02, 0.02, 0.01, respectively) than the comparison group. Individual OSCE component assessments showed significant improvements in the special musculoskeletal physical examination test. The overall duration and amount of participants' hands-on time were significantly longer for the multimodal than for the traditional bedside teaching group (p = 0.01 and 0.01, respectively), and the facilitator's demonstration time was significantly shorter (p = 0.01). The multimodal learner-centered teaching approach evaluated in this study was effective for teaching MPES. It appeared to maximize learner engagement through enhancing interactions and providing increased time to engage in hands-on practice. This teaching approach improved MPES levels, maximized teaching efficiency for scenarios with limited instruction time and resources, and enhanced competency of undergraduate medical students in performing special musculoskeletal physical examinations compared to traditional bedside teaching.

Project description:BackgroundLearning to interpret electrocardiograms (ECGs) is a crucial objective in medical education. Despite its importance, errors in ECGs interpretation are common, and the optimal teaching methods have not yet been clearly established.ObjectivesTo evaluate students' confidence in ECGs analysis and their opinion on current teaching methods, and to assess the effectiveness of a new ECG educational approach.MethodsFirst, we conducted a survey on ECG learning among fourth to sixth-year medical students. Second, a 5-week multicenter comparative study was conducted with fourth-year medical students during their cardiology internship. Two different teaching methods were used, assigned by center. The first group participated in 5-minutes workshops 4 times a week using a "reversed classroom" method, supervised by a cardiologist, where students took turns selecting, presenting and discussing ECGs. The control group attended a single 2-hour face-to-face ECG course. All participants completed a 30-minute ECGs analysis test at baseline and after 5 weeks.ResultsOut of 401 survey respondents, the confidence levels in ECG interpretation were 3/5 (IQR 2-3) for routine situations and 2/5 (IQR 1-3) for emergency situations. Satisfaction with ECG teaching was low (2/5, IQR 1-3) and 96.3% of respondents favored more extensive ECG training. In the comparative study, 52 students from 3 medical schools were enrolled (control group: n = 27; workshop group: n = 25). Both groups showed significant improvement in exam scores from baseline to 5-week (33/100 ± 12/100 to 44/100 ± 12/100, p < 0.0001 for the control group and 36/100 ± 13/100 to 62/100 ± 12/100, p < 0.0001 for the workshop group). The improvement was significantly greater in the workshop group compared to the control group (+ 26 ± 11 vs. + 11 ± 6, p < 0.001).ConclusionsAmong French medical students who initially reported low confidence and insufficient skills in ECG interpretation, the workshop approach using a "reversed classroom" method was found to be more effective than conventional lecture-based teaching during cardiology internship.

Dataset Information

Enhancing tertiary students' programming skills with an explainable Educational Data Mining approach.

Publications

Enhancing tertiary students' programming skills with an explainable Educational Data Mining approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets