| Item type |
SIG Technical Reports(1) |
| 公開日 |
2024-03-16 |
| タイトル |
|
|
タイトル |
Students' Performance Prediction based on Similarity between Online Textbooks and Questions |
| タイトル |
|
|
言語 |
en |
|
タイトル |
Students' Performance Prediction based on Similarity between Online Textbooks and Questions |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
一般セッション5B |
| 資源タイプ |
|
|
資源タイプ識別子 |
http://purl.org/coar/resource_type/c_18gh |
|
資源タイプ |
technical report |
| 著者所属 |
|
|
|
Graduate School of Information Science and Electrical Engineering, Kyushu University |
| 著者所属 |
|
|
|
Faculty of Information Science and Electrical Engineering, Kyushu University |
| 著者所属 |
|
|
|
Promotion Office for Data-Driven Innovation, Kyushu University |
| 著者所属 |
|
|
|
Research Institute for Information Technology, Kyushu University |
| 著者所属 |
|
|
|
Faculty of Information Science and Electrical Engineering, Kyushu University |
| 著者所属 |
|
|
|
Faculty of Information Science and Electrical Engineering, Kyushu University |
| 著者所属(英) |
|
|
|
en |
|
|
Graduate School of Information Science and Electrical Engineering, Kyushu University |
| 著者所属(英) |
|
|
|
en |
|
|
Faculty of Information Science and Electrical Engineering, Kyushu University |
| 著者所属(英) |
|
|
|
en |
|
|
Promotion Office for Data-Driven Innovation, Kyushu University |
| 著者所属(英) |
|
|
|
en |
|
|
Research Institute for Information Technology, Kyushu University |
| 著者所属(英) |
|
|
|
en |
|
|
Faculty of Information Science and Electrical Engineering, Kyushu University |
| 著者所属(英) |
|
|
|
en |
|
|
Faculty of Information Science and Electrical Engineering, Kyushu University |
| 著者名 |
Yongle, Ren
Cheng, Tang
Yuta, Taniguchi
Tsubasa, Minematsu
Fumiya, Okubo
Atsushi, Shimada
|
| 著者名(英) |
Yongle, Ren
Cheng, Tang
Yuta, Taniguchi
Tsubasa, Minematsu
Fumiya, Okubo
Atsushi, Shimada
|
| 論文抄録 |
|
|
内容記述タイプ |
Other |
|
内容記述 |
In university education, predicting students' performance is important for assessing their mastery of specific knowledge areas and offering feedback. To overcome limitations in existing grade predictions that overlook students' knowledge mastery, we propose an approach to predict performance on individual exam questions. This method utilizes cosine similarity calculations to establish relationships between exam questions and their connections to online textbooks, creating a new dataset from 494 students across four undergraduate courses. We evaluated the performance of four machine-learning methods, achieving an AUC score exceeding 0.7 through 5-fold cross-validation. We applied feature weighting by multiplying cosine similarity scores to enhance correlation with the prediction target. The results show an improvement of more than 0.1 in the AUC score over the other cases. The contribution of this work is the introduction of an effective method for predicting students' exam performance. |
| 論文抄録(英) |
|
|
内容記述タイプ |
Other |
|
内容記述 |
In university education, predicting students' performance is important for assessing their mastery of specific knowledge areas and offering feedback. To overcome limitations in existing grade predictions that overlook students' knowledge mastery, we propose an approach to predict performance on individual exam questions. This method utilizes cosine similarity calculations to establish relationships between exam questions and their connections to online textbooks, creating a new dataset from 494 students across four undergraduate courses. We evaluated the performance of four machine-learning methods, achieving an AUC score exceeding 0.7 through 5-fold cross-validation. We applied feature weighting by multiplying cosine similarity scores to enhance correlation with the prediction target. The results show an improvement of more than 0.1 in the AUC score over the other cases. The contribution of this work is the introduction of an effective method for predicting students' exam performance. |
| 書誌レコードID |
|
|
収録物識別子タイプ |
NCID |
|
収録物識別子 |
AA12496725 |
| 書誌情報 |
研究報告教育学習支援情報システム（CLE）
巻 2024-CLE-42,
号 19,
p. 1-8,
発行日 2024-03-16
|
| ISSN |
|
|
収録物識別子タイプ |
ISSN |
|
収録物識別子 |
2188-8620 |
| Notice |
|
|
|
SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc. |
| 出版者 |
|
|
言語 |
ja |
|
出版者 |
情報処理学会 |
IPSJ-CLE24042019.pdf (1.2 MB)
