Deep Item Response Theory as a Novel Test Theory Based on Deep Learning
Item Response Theory (IRT) evaluates, on the same scale, examinees who take different tests. It requires the linkage of examinees’ ability scores as estimated from different tests. However, the IRT linkage techniques assume independently random sampling of examinees’ abilities from a standard normal...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/9/1020 |
| _version_ | 1797536371229851648 |
|---|---|
| author | Emiko Tsutsumi Ryo Kinoshita Maomi Ueno |
| author_facet | Emiko Tsutsumi Ryo Kinoshita Maomi Ueno |
| author_sort | Emiko Tsutsumi |
| collection | DOAJ |
| description | Item Response Theory (IRT) evaluates, on the same scale, examinees who take different tests. It requires the linkage of examinees’ ability scores as estimated from different tests. However, the IRT linkage techniques assume independently random sampling of examinees’ abilities from a standard normal distribution. Because of this assumption, the linkage not only requires much labor to design, but it also has no guarantee of optimality. To resolve that shortcoming, this study proposes a novel IRT based on deep learning, Deep-IRT, which requires no assumption of randomly sampled examinees’ abilities from a distribution. Experiment results demonstrate that Deep-IRT estimates examinees’ abilities more accurately than the traditional IRT does. Moreover, Deep-IRT can express actual examinees’ ability distributions flexibly, not merely following the standard normal distribution assumed for traditional IRT. Furthermore, the results show that Deep-IRT more accurately predicts examinee responses to unknown items from the examinee’s own past response histories than IRT does. |
| first_indexed | 2024-03-10T11:58:45Z |
| format | Article |
| id | doaj.art-399700cec216416c8a138b0f586e8f39 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T11:58:45Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-399700cec216416c8a138b0f586e8f392023-11-21T17:04:28ZengMDPI AGElectronics2079-92922021-04-01109102010.3390/electronics10091020Deep Item Response Theory as a Novel Test Theory Based on Deep LearningEmiko Tsutsumi0Ryo Kinoshita1Maomi Ueno2Department of Information and Network Engineering, The University of Electro-Communications, Tokyo 182-8585, JapanDepartment of Information and Network Engineering, The University of Electro-Communications, Tokyo 182-8585, JapanDepartment of Information and Network Engineering, The University of Electro-Communications, Tokyo 182-8585, JapanItem Response Theory (IRT) evaluates, on the same scale, examinees who take different tests. It requires the linkage of examinees’ ability scores as estimated from different tests. However, the IRT linkage techniques assume independently random sampling of examinees’ abilities from a standard normal distribution. Because of this assumption, the linkage not only requires much labor to design, but it also has no guarantee of optimality. To resolve that shortcoming, this study proposes a novel IRT based on deep learning, Deep-IRT, which requires no assumption of randomly sampled examinees’ abilities from a distribution. Experiment results demonstrate that Deep-IRT estimates examinees’ abilities more accurately than the traditional IRT does. Moreover, Deep-IRT can express actual examinees’ ability distributions flexibly, not merely following the standard normal distribution assumed for traditional IRT. Furthermore, the results show that Deep-IRT more accurately predicts examinee responses to unknown items from the examinee’s own past response histories than IRT does.https://www.mdpi.com/2079-9292/10/9/1020deep learninge-testingtest theoryitem response theory |
| spellingShingle | Emiko Tsutsumi Ryo Kinoshita Maomi Ueno Deep Item Response Theory as a Novel Test Theory Based on Deep Learning Electronics deep learning e-testing test theory item response theory |
| title | Deep Item Response Theory as a Novel Test Theory Based on Deep Learning |
| title_full | Deep Item Response Theory as a Novel Test Theory Based on Deep Learning |
| title_fullStr | Deep Item Response Theory as a Novel Test Theory Based on Deep Learning |
| title_full_unstemmed | Deep Item Response Theory as a Novel Test Theory Based on Deep Learning |
| title_short | Deep Item Response Theory as a Novel Test Theory Based on Deep Learning |
| title_sort | deep item response theory as a novel test theory based on deep learning |
| topic | deep learning e-testing test theory item response theory |
| url | https://www.mdpi.com/2079-9292/10/9/1020 |
| work_keys_str_mv | AT emikotsutsumi deepitemresponsetheoryasanoveltesttheorybasedondeeplearning AT ryokinoshita deepitemresponsetheoryasanoveltesttheorybasedondeeplearning AT maomiueno deepitemresponsetheoryasanoveltesttheorybasedondeeplearning |