Knowledge Graph-Assisted Multi-task Feature-Based Course Recommendation Algorithm

doi:10.3778/j.issn.1002-8331.2010-0287

Abstract

Abstract:

When collecting online learning information, there is a general lack of data, which makes the recommendation of course resources may be unsatisfactory due to sparse data. In order to solve the above problems, this paper proposes a Multi-Layer Knowledge graph Recommendation（MLKR） algorithm based on an end-to-end deep learning framework that incorporates knowledge graphs. Based on multi-task feature learning, the knowledge graph is embedded in the tasks. Higher-order connections between potential features and entities are established by cross-compression units between tasks to build recommendation models. Accurate recommendation of course resources based on learners’goals, interests and knowledge levels is realized. The experimental results show that the training time and prediction accuracy of MLKR recommendation algorithm are better than the collaborative filtering algorithm and logistic regression model based on users or items, and it has certain application value in the field of course resource recommendation.

Key words: knowledge graph, collaborative filtering, recommendation algorithms, educational big data, Multi-Layer Knowledge graph Recommendation（MLKR） algorithm

摘要：

在采集在线学习信息时，普遍存在数据缺失的情况，使得课程资源推荐时可能因数据稀疏导致推荐的效果不理想。为了解决上述问题，基于端对端的深度学习框架，提出了融合知识图谱的多任务特征推荐算法（Multi-Layer Knowledge graph Recommendation，MLKR）。基于多任务特征学习，在任务中嵌入知识图谱；在任务之间通过交叉压缩单元建立潜在特征和实体之间的高阶联系，从而建立推荐模型。实现了基于学习者目标、兴趣、知识水平的课程资源精准推荐。实验结果表明，MLKR推荐算法训练时长和预测准确率均优于基于用户或物品的协同过滤算法和逻辑回归模型，在课程资源推荐领域具有一定的应用价值。

关键词: 知识图谱, 协同过滤, 推荐算法, 教育大数据, 多任务课程推荐（MLKR）算法

WU Hao, XU Xingjian, MENG Fanjun. Knowledge Graph-Assisted Multi-task Feature-Based Course Recommendation Algorithm[J]. Computer Engineering and Applications, 2021, 57(21): 132-139.

吴昊，徐行健，孟繁军. 课程资源的融合知识图谱多任务特征推荐算法[J]. 计算机工程与应用, 2021, 57(21): 132-139.

References

[1] 于朝晖.CNNIC发布《第45次中国互联网络发展状况统计报告》[J].网信军民融合，2020（5）：26-27.
YU Zhaohui.China Internet Network Information Center（CNNIC）.The 45th statistical report on the current situation of Internet development in China[J].Civil-Miltary Integration on Cyberspace，2020（5）：26-27.
[2] 叶露.在线学习资源个性化推荐与学习路径规划研究[D].杭州：浙江财经大学，2018.
YE L.Personalized recommendation of online learning resources and learning path planning[D].Hangzhou：Zhejiang University of Finance and Economics，2018.
[3] DOR?A F.A.Automatic student modeling in adaptive educational systems through probabilistic learning style combinations：a qualitative comparison between two innovative stochastic approaches[J].Journal of the Brazilian Computer Society，2013，19（1）：43-58.
[4] 庞颖，吴锦程.试论MOOC对当前大学生职业能力培训的影响[J].高等继续教育学报，2015，28（5）：21-24.
PANG Y，WU J C.The influence of MOOCs on the vocational competency training of current students[J].Journal of Advanced Continuing Education，2015，28（5）：21-24.
[5] Online courses from Harvard and MIT[EB/OL].[2016-08-03].https：//www.kaggle.com/edx/course-study.
[6] 宋茜.构建基于网络的个性化学习环境[C]//第六届全球华人研究计算机教育应用大会，2002：824-830.
SONG X.Building a Web-based personalized learning environment[C]//Proceedings of the Sixth Global Chinese Conference on Research Computer Applications in Education，2002：824-830.
[7] 王忠华，余艳.网络课程的个性化及其构建[J].现代教育技术，2008（3）：79-83.
WANG Z H，YU Y.Personalization and construction of online courses[J].Modern Educational Technology，2008（3）：79-83.
[8] 李星雨，宋娜，何锦儿，等.基于协同过滤算法的个性化课程推荐服务[J].现代信息科技，2019，3（24）：121-123.
LI X Y，SONG N，HE J E，et al.Personalized course recommendation service based on collaborative filtering algorithm[J].Modern Information Technology，2019，3（24）：121-123.
[9] 檀晓红.基于推荐及遗传算法的个性化课程生成与进化研究[D].上海：上海交通大学，2013.
TANG X H.Personalized curriculum generation and evolution based on recommendations and genetic algorithms[D].Shanghai：Shanghai Jiao Tong University，2013.
[10] AGUILAR J，VALDIVIEZO-DIAZ P，RIOFRIS G.A general framework for intelligent recommender systems[J].Applied Computing and Informatics，2016.
[11] PANG Y，JIN Y，ZHANG Y，et al.Collaborative filtering recommendation for MOOC application[J].Computer Applications in Engineering Education，2017，25（1）：120-128.
[12] 郭清菊.推荐系统算法在学生个性化选课中的应用研究[D].中山：中山大学，2013.
GUO Qingju.Application of recommendation system algorithm in students’ personalized course selection[D].Zhongshan：Sun Yat-sen University，2013.
[13] 胡文韬.基于知识图谱的学习路径图生成技术研究[D].北京：北京邮电大学，2017.
HU W T.Research on knowledge graph-based learning path map generation techniques[D].Beijing：Beijing University of Posts and Telecommunications，2017.
[14] 丁恒，黄全舟.基于属性特征的个性化旅游推荐算法研究[J].智能计算机与应用，2020，10（1）：193-196.
DING H，HUANG Q Z.Research on attribute based personalized travel recommendation algorithm[J].Smart Computers and Applications，2020，10（1）：193-196.
[15] 张忠平，郭献丽.一种优化的基于项目评分预测的协同过滤推荐算法[J].计算机应用研究，2008（9）：2658-2660.
ZHANG Z P，GUO X L.An optimised collaborative filtering recommendation algorithm based on project score prediction[J].Application Research of Computers，2008（9）：2658-2660.
[16] 李浩，张亚钏，康雁，等.融合循环知识图谱和协同过滤电影推荐算法[J].计算机工程与应用，2020，56（2）：106-114.
LI H，ZHANG Y C，KANG Y，et al.Fusion of circular knowledge graphs and collaborative filtering algorithms for movie recommendation[J]Computer Engineering and Applications，2020，56（2）：106-114.
[17] WANG H W，ZHANG F Z，ZHAO M，et.al.Multi-task featurelearning for knowledge graph enhanced recommendation[C]//Proceedings of the World Wide Web Conference.New York：ACM，2019：2000-2010.
[18] WANG H W，ZHANG F Z，WANG J L，et al.Ripple-Net：propagating user preferences on the knowledge graph for recommender systems[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management.Torino：ACM，2018：417-426.
[19] WANG H W，ZHANG F Z，XIE X，et al.DKN：deep knowledge-aware network for news recommendation[C]//Proceedings of the 27th World Wide Web Conference on World Wide Web.Lyon：ACM，2018：1835-1844.
[20] YOSINSKI J，CLUNE J，BENGIO Y，et al.How transferable are features in deep neural networks?[C]//International Conference on Neural Information Processing Systems.[S.l.]：MIT Press，2014.
[21] 陆桂明，张源，周志敏.基于机器学习的贫困生分类预测研究[J].计算机应用与软件，2019，36（1）：316-319.
LU G M，ZHANG Y，ZHOU Z M.Machine learning based classification and prediction study of poor students[J].Computer Applications and Software，2019，36（1）：316-319.
[22] 程志君，罗鹏程，罗玉文.基于开放数据的edX课程学习者行为及相关因素分析[J].高等教育研究学报，2017，40（4）：46-49.
CHENG Z J，LUO P C，LUO Y W.Open data-based analysis of learner behaviour and related factors in edX courses[J].Journal of Higher Education Studies，2017，40（4）：46-49.
[23] 顾明星，黄伟建，黄远，等.结合用户聚类与改进用户相似性的协同过滤推荐[J].计算机工程与应用，2020，56（22）：185-190.
GU X X，HUANG W J，HUANG Y，et al.Co-operative filtering recommendations combining user clustering with improved user similarity[J].Computer Engineering and Applications，2020，56（22）：185-190.