One-minute Paper as a Basis of Automatic Prediction of Student’s Grade

ID: 49443 Type: Full Paper: Systems & Resources
  1. Yoshio Yamagishi, Kanazawa Institute of Technology, Japan

Wednesday, June 29 4:00-4:30 PM Location: Pavilion Ballroom D

No presider for this session.

Abstract: One-minute paper (OMP), which is usually assigned at the end of a class and requires students to write down about the class in a minute or two, may reflect student’s learning level. We explore the potentiality of OMP as a basis of automatic prediction of student’s grade. Total 2198 OMPs were collected in our lecture named “Fundamental Programing”, which is for the first year students of Department of Media Informatics, Kanazawa Institute of Technology for two years. Those OMPs were inputted to three classifiers based on different machine learning algorithms such as Naïve Bayes, Support Vector Machine and Convolution Neural Network, and we found that the accuracies of these three classifiers are 30%, 39% and 40% respectively. The correlation between student’s final grade and number of OMP submission is also investigated. We found positive correlation (R=0.57) between them, and the prediction accuracy based on the linear regression is 29%


Conference attendees are able to comment on papers, view the full text and slides, and attend live presentations. If you are an attendee, please login to get full access.