spheredata - Students' Performance Dataset in Physics Education Research (SPHERE)

A multidimensional dataset of students' performance assessment in high school physics. The SPHERE dataset was collected from 497 students in four public high schools specifically measuring their conceptual understanding, scientific ability, and attitude toward physics [see Santoso et al. (2024) <doi:10.17632/88d7m2fv7p.1>]. The data collection was conducted using some research based assessments established by the physics education research community. They include the Force Concept Inventory, the Force and Motion Conceptual Evaluation, the Rotational and Rolling Motion Conceptual Survey, the Fluid Mechanics Concept Inventory, the Mechanical Waves Conceptual Survey, the Thermal Concept Evaluation, the Survey of Thermodynamic Processes and First and Second Laws, the Scientific Abilities Assessment Rubrics, and the Colorado Learning Attitudes about Science Survey. Students' attributes related to gender, age, socioeconomic status, domicile, literacy, physics identity, and test results administered using teachers' developed items are also reported in this dataset.

Last updated 4 months ago

3.81 score 32 scripts 492 downloads

sphereML - Analyzing Students' Performance Dataset in Physics Education Research (SPHERE) using Machine Learning (ML)

A shiny R package facilitating ML based analysis for physics education research (PER) purposes. The data has been made available in the CRAN repository through the spheredata package. SPHERE stands for Students' Performance in Physics Education Research (PER). The students are the eleventh graders learning physics at high school curriculum. We follow the stream of multidimensional students' assessment as probed by some research based assessments (RBAs) in PER. The goal is to predict the students' performance at the end of the learning process. Three learning domains are measured including conceptual understanding, scientific ability, and scientific attitude. Furthermore, demographic backgrounds and potential variables influencing students' performance on physics are also demonstrated. We provide teachers' judgment data as our baseline to compare the predictive results of students' performance between machine learning (ML) based analysis and teacher (human) based judgment. Click on the Tab below to explore the detail of each data further.

Last updated 3 months ago

2.00 score