TY - JOUR
KW - Automated Short Answer Scoring
KW - Hybrid Transfer Learning
KW - Student Answer Dataset
KW - Trustworthy System
AU - Martinus Maslim
AU - Hei-Chia Wang
AU - Cendra Devayana Putra
AU - Yulius Denny Prabowo
AB - To measure the quality of student learning, teachers must conduct evaluations. One of the most efficient modes of evaluation is the short answer question. However, there can be inconsistencies in teacher-performed manual evaluations due to an excessive number of students, time demands, fatigue, etc. Consequently, teachers require a trustworthy system capable of autonomously and accurately evaluating student answers. Using hybrid transfer learning and student answer dataset, we aim to create a reliable automated short answer scoring system called Hybrid Transfer Learning for Automated Short Answer Scoring (HTL-ASAS). HTL-ASAS combines multiple tokenizers from a pretrained model with the bidirectional encoder representations from transformers. Based on our evaluation of the training model, we determined that HTL-ASAS has a higher evaluation accuracy than models used in previous studies. The accuracy of HTL-ASAS for datasets containing responses to questions pertaining to introductory information technology courses reaches 99.6%. With an accuracy close to one hundred percent, the developed model can undoubtedly serve as the foundation for a trustworthy ASAS system.
IS - Special issue on Generative Artificial Intelligence in Education
M1 - 5
N2 - To measure the quality of student learning, teachers must conduct evaluations. One of the most efficient modes of evaluation is the short answer question. However, there can be inconsistencies in teacher-performed manual evaluations due to an excessive number of students, time demands, fatigue, etc. Consequently, teachers require a trustworthy system capable of autonomously and accurately evaluating student answers. Using hybrid transfer learning and student answer dataset, we aim to create a reliable automated short answer scoring system called Hybrid Transfer Learning for Automated Short Answer Scoring (HTL-ASAS). HTL-ASAS combines multiple tokenizers from a pretrained model with the bidirectional encoder representations from transformers. Based on our evaluation of the training model, we determined that HTL-ASAS has a higher evaluation accuracy than models used in previous studies. The accuracy of HTL-ASAS for datasets containing responses to questions pertaining to introductory information technology courses reaches 99.6%. With an accuracy close to one hundred percent, the developed model can undoubtedly serve as the foundation for a trustworthy ASAS system.
PY - 2024
SE - 37
SP - 37
EP - 45
T2 - International Journal of Interactive Multimedia and Artificial Intelligence
TI - A Trustworthy Automated Short-Answer Scoring System Using a New Dataset and Hybrid Transfer Learning Method
UR - https://www.ijimai.org/journal/bibcite/reference/3418
VL - 8
SN - 1989-1660
ER -