联合神经协同过滤与短期偏好的课程推荐模型  

Course recommendation model combined neural collaborative filtering and short-term preference

作　　者：罗琨杰 张珑 杨波 孙华志[1] LUO Kunjie;ZHANG Long;YANG Bo;SUN Huazhi(College of Computer and Information Engineering,Tianjin Normal University,Tianjin 300387,China)

机构地区：[1]天津师范大学计算机与信息工程学院,天津300387

出　　处：《天津师范大学学报（自然科学版）》2022年第5期59-65,共7页Journal of Tianjin Normal University：Natural Science Edition

基　　金：国家自然科学基金面上资助项目(61771173);天津市自然科学基金重点资助项目(20JCZDJC00400).

摘　　要：提出一种联合神经协同过滤与短期偏好的课程推荐模型.该模型通过利用学习者近期的学习行为捕获短期偏好,用以平衡或辅助学习者兴趣变化前后的各时刻历史行为,建构其动态兴趣赋能的历史行为新贡献度,基于短期偏好来重构学习者个性化动态学习兴趣,从而进行高效的课程推荐.利用学堂在线真实MOOC数据集进行验证,实验结果表明,与其他模型相比,该模型的HR和NDCG指标均得到一定提升,且模型鲁棒性较强.A course recommendation model combined neural collaborative filtering and short-term preference is proposed.Learners′recent learning behaviors are used to capture short-term preferences,which can be used to balance or assist learners′historical behaviors at various moments before and after interest changes,and their new contributions of dynamic interest-enabled historical behaviors are constructed.Learners′personalize dynamic learning interest are reconstructed based on short-term preference,so as to make efficient course recommendation.The actual MOOC data from xuetangx.com is used for experimental verification.The results show that,compared with other models,the HR and NDCG indexes of this model are improved,and the model has strong robustness.

关 键 词：历史贡献度 个性化学习兴趣 短期偏好 课程推荐 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]