Predicting Physics Students’ Achievement Using In-class Assessment Data: A Comparison of Two Machine Learning Models (70849)

Session Information: Assessment Theories & Methodologies
Session Chair: Hsiao-Chi Ho

Thursday, 23 November 2023 09:25
Session: Session 1
Room: Room 608
Presentation Type: Oral Presentation

All presentation times are UTC + 9 (Asia/Tokyo)

Data is the primary source to scaffold physics teaching and learning both for teacher and student as mainly reported through in-class assessment. Machine learning (ML) is an axis of artificial intelligence (AI) study that greatly attract for the development into physics education research (PER). ML is built to predict students’ learning that can support students’ success to an effective physics achievement. In this paper, two ML algorithms, logistic regression and random forest, had been trained and compared to predict students’ achievement on high school physics (N = 197). Data of students’ achievement was harvested from in-class assessment administered by a physics teacher in terms of knowledge (cognitive) and psychomotor during 2020/2021 academic year. Three assessment points of knowledge and psychomotor were employed to predict students’ achievement as dichotomous scale on the final term examination. By combining in-class assessment of knowledge and psychomotor, we could discover plausible performance of students’ achievement prediction using the two algorithms. Aspect of knowledge assessment was the determinant factor in predicting high school physics students’ achievement. Findings reported by this paper recommended open room for the ML implementation for educational practice as well its potential contribution to support physics teaching and learning.

Authors:
Purwoko Haryadi Santoso, Universitas Negeri Yogyakarta, Indonesia
Hayang Sugeng Santosa, Universitas Muhammadiyah, Indonesia
Edi Istiyono, Universitas Negeri Yogyakarta, Indonesia
Haryanto Haryanto, Universitas Negeri Yogyakarta, Indonesia
Heri Retnawati, Universitas Negeri Yogyakarta, Indonesia


About the Presenter(s)
Mr Purwoko Haryadi Santoso is a University Doctoral Student at Universitas Negeri Yogyakarta in Indonesia

See this presentation on the full scheduleThursday Schedule



Conference Comments & Feedback

Place a comment using your LinkedIn profile

Comments

Share on activity feed

Powered by WP LinkPress

Share this Presentation

Posted by Clive Staples Lewis

Last updated: 2023-02-23 23:45:00