Multi-Feature Fusion Based Model for MOOC Recommendation

doi:10.3778/j.issn.1002-8331.2201-0094

Abstract

Abstract: In order to make full use of the contextual information of MOOC（massive open online course） and accurately represent the feature of learners and courses, a multi-feature fusion based model for MOOC recommendation（MFF-MOOCREC） is proposed. Text convolutional neural network as well as bidirectional long short-term memory network are introduced respectively to capture the textual and sequential feature from data, and a multi-level attention mechanism is designed to extract key information from learning records, review texts and multiple attributes of course. In order to increase the coverage ratio of recommendation, prefix-projected pattern growth and affinity propagation algorithm are adopted in combination for a relevant clustering analysis on the original courses’ category labels. Probabilistic matrix factorization is used for parameters training, and the predicted ratings are obtained from the dot product between learners’ latent vectors and courses’ latent vectors. Experiments show that, compared with the available methods, MFF-MOOCREC achieves the improvements of average 46.86%, 41.19%, 10.95% and 44.08%, 28.79%, 9.81% on hit ratio, normalized discounted cumulative gain and coverage ratio indicators over Coursera dataset and iCourse dataset respectively, which indicates the proposed model can effectively alleviate the problem of data sparseness as well as improve the performance of recommendation to some extent.

Key words: MOOC recommendation, text convolutional neural network, bidirectional long short-term memory network, attention mechanism, relevant clustering analysis, probabilistic matrix factorization

摘要： 为充分利用MOOC（massive open online course）上下文信息，精确表示学习者和课程特征，提出一种多特征融合的MOOC推荐模型（multi-feature fusion based model for MOOC recommendation，MFF-MOOCREC）。利用文本卷积神经网络和双向长短时记忆网络捕获数据中的文本和时序特征，并设计多级注意力机制提取学习者交互序列、评论文本和课程多元属性中的关键信息；基于前缀投影的模式挖掘和亲和力传播算法对原始课程类别进行关联聚类分析以增加推荐的覆盖率；采用概率矩阵分解训练模型参数，将优化后的学习者隐向量和课程隐向量点乘产生预测评分。实验表明，和现有推荐方法相比，MFF-MOOCREC的命中率、归一化折损累计增益和覆盖率指标在Coursera数据集上平均提高46.86%、41.19%和10.95%，在iCourse数据集上平均提高44.08%、28.79%和9.81%，对于缓解数据稀疏问题，提升推荐质量具有一定优势。

SHU Xinfeng, CAO Wangmei, WANG Shuyan. Multi-Feature Fusion Based Model for MOOC Recommendation[J]. Computer Engineering and Applications, 2023, 59(10): 123-133.

舒新峰, 曹望美, 王曙燕. 多特征融合的MOOC推荐模型[J]. 计算机工程与应用, 2023, 59(10): 123-133.

References

[1] DOJA M N.An improved recommender system for E-learning environments to enhance learning capabilities of learners[C]//Proceedings of ICETIT 2019：Emerging Trends in Information Technology.Cham：Springer，2020：604-612.
[2] RAWLINGS D，TIEMAN J，MOORES C.E-learning：who uses it and what difference does it make?[J].International Journal of Palliative Nursing，2019，25（10）：482-493.
[3] WONG J，KHALIL M，BAARS M，et al.Exploring sequences of learner activities in relation to self-regulated learning in a massive open online course[J].Computers & Education，2019，140：103595.
[4] 中国慕课数量和应用规模居世界第一[EB/OL].（2020-12-13）[2022-03-05].https：//baijiahao.baidu.com/s?id=16859703577
65205927&wfr=spider&for=pc.
China builds largest pool of MOOCs[EB/OL].（2020-12-13）[2022-03-05].https：//baijiahao.baidu.com/s?id=16859703577
65205927&wfr=spider&for=pc.
[5] FENG W，TANG J，LIU T X.Understanding dropouts in MOOCs[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence，2019：517-524.
[6] LI L，JOHNSON J，AARHUS W，et al.Key factors in MOOC pedagogy based on NLP sentiment analysis of learner reviews：what makes a hit[J].Computers & Education，2022，176：104354.
[7] LI H，LI H，ZHANG S，et al.Intelligent learning system based on personalized recommendation technology[J].Neural Computing and Applications，2019，31（9）：4455-4462.
[8] HIDAYAT A F，SUWAWI D D J，LAKSITOWENING K A.Learning content recommendations on personalized learning environment using collaborative filtering method[C]//Proceedings of the 2020 8th International Conference on Information and Communication Technology.Piscataway：IEEE，2020：1-6.
[9] 刘芳，田枫，李欣，等.融入学习者模型在线学习资源协同过滤推荐方法[J].智能系统学报，2021，16（6）：1117-1125.
LIU F，TIAN F，LI X，et al.A collaborative filtering recommendation method for online learning resources incorporating the learner model[J].CAAI Transactions on Intelligent Systems，2021，16（6）：1117-1125.
[10] 胡园园，姜文君，任德盛，等.一种结合用户适合度和课程搭配度的在线课程推荐方法[J].计算机研究与发展，2022，59（11）：2520-2533.
HU Y Y，JIANG W J，REN D S，et al.Integrating user suitability and course matching degree for online course recommendation[J].Journal of Computer Research and Development，2022，59（11）：2520-2533.
[11] GURUGE D B，KADEL R，HALDER S J.The state of the art in methodologies of course recommender systems—a review of recent research[J].Data，2021，6（2）：18.
[12] SYMEONIDIS P，MALAKOUDIS D.Multi-modal matrix factorization with side information for recommending massive open online courses[J].Expert Systems with Applications，2019，118：261-271.
[13] 廖宏建，谢亮，曲哲.一种基于隐式信任感知的MOOCs推荐方法[J].情报理论与实践，2021，44（2）：128-135.
LIAO H J，XIE L，QU Z.A recommendation method for MOOCs based on implicit trust-awareness[J].Information Studies：Theory & Application，2021，44（2）：128-135.
[14] ZHANG S，YAO L，SUN A，et al.Deep learning based recommender system：a survey and new perspectives[J].ACM Computing Surveys，2019，52（1）：1-38.
[15] ZHANG H，HUANG T，LV Z，et al.MOOCRC：a highly accurate resource recommendation model for use in MOOC environments[J].Mobile Networks and Applications，2019，24（1）：34-46.
[16] XU W，ZHOU Y.Course video recommendation with multimodal information in online learning platforms：a deep learning framework[J].British Journal of Educational Technology，2020，51（5）：1734-1747.
[17] 厉小军，柳虹，施寒潇，等.基于深度学习的课程推荐模型[J].浙江大学学报（工学版），2019，53（11）：2139-2145.
LI X J，LIU H，SHI H X，et al.Deep learning based course recommendation model[J].Journal of Zhejiang University（Engineering Science），2019，53（11）：2139-2145.
[18] LI X，LI X，TANG J，et al.Improving deep item-based collaborative filtering with bayesian personalized ranking for MOOC course recommendation[C]//Proceedings of the 2020 International Conference on Knowledge Science，Engineering and Management.Cham：Springer，2020：247-258.
[19] TAN J，CHANG L，LIU T，et al.Attentional autoencoder for course recommendation in MOOC with course relevance[C]//Proceedings of the 2020 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery.Piscataway：IEEE，2020：190-196.
[20] WANG J，XIE H，WANG F L，et al.Top-N personalized recommendation with graph neural networks in MOOCs[J].Computers and Education：Artificial Intelligence，2021，2：100010.