[Li, Qing; Sun, Jianwen] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan, Peoples R China.
[Lu, Zijian; Zhou, Jianpeng; Zhang, Kai] Cent China Normal Univ, Natl Engn Res Ctr Learning, Wuhan, Peoples R China.
通讯机构：
[Zhang, Kai] C
Cent China Normal Univ, Natl Engn Res Ctr Learning, Wuhan, Peoples R China.
语种：
英文
关键词：
Data visualization;Embeddings;Students;Benchmark datasets;Embedding method;Future performance;Knowledge tracings;Model performance;Collaborative filtering
期刊：
Lecture Notes in Computer Science
ISSN：
0302-9743
年：
2021
卷：
12816
页码：
333-342
会议名称：
14th International Conference on Knowledge Science, Engineering and Management, KSEM 2021
会议论文集名称：
Lecture Notes in Artificial Intelligence
会议时间：
14 August 2021 through 16 August 2021
会议地点：
Tokyo, JAPAN
会议主办单位：
[Sun, Jianwen;Li, Qing] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan, Peoples R China.^[Zhou, Jianpeng;Zhang, Kai;Lu, Zijian] Cent China Normal Univ, Natl Engn Res Ctr Learning, Wuhan, Peoples R China.
会议赞助商：
Springer LNCS, Waseda Univ, N Amer Chinese Talents Assoc, Longxiang High Tech Grp Inc
主编：
Qiu, H Zhang, C Fei, Z Qiu, M Kung, SY
出版地：
GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND
出版者：
Springer Science and Business Media Deutschland GmbH
Acknowledgements. This research is supported by National Natural Science Foundation of China (62077021, 62077018, 61807012), Humanity and Social Science Youth Foundation of Ministry of Education of China (20YJC880083), and Teaching Research Funds for Undergraduates and Postgraduates of CCNU.
机构署名：
本校为第一且通讯机构
院系归属：
国家数字化学习工程技术研究中心
摘要：
Knowledge tracing predicts students’ future performance based on their past performance. Most of the existing models take skills as input, which neglects question information and further limits the model performance. Inspired by item-item collaborative filtering in recommender systems, we propose a question-question Collaborative embedding method for Knowledge Tracing (CoKT) to introduce question information. To be specific, we incorporate student-question interactions and question-skill relations to capture question similarity. Based on the s...
