Abstract | ||
---|---|---|
In online learning platforms, personalized course recommendation services can significantly improve users' interest and learning efficiency. A hybrid recommendation model, which comprehensively takes the timeliness of courses and the implicit interests of students into consideration, is proposed to improve the diversity of recommendation methods and solve the problem of data sparsity in the existing online learning platforms. Experiments on the massive open online course (MOOC) dataset of Chinese universities show that the proposed model has improved the performance of course recommendations to a certain extent without excessively increasing the algorithm's complexity. |
Year | DOI | Venue |
---|---|---|
2022 | 10.2316/J.2022.206-0774 | INTERNATIONAL JOURNAL OF ROBOTICS & AUTOMATION |
Keywords | DocType | Volume |
Recommendation system, factorization machine, collaborative filtering, timeliness | Journal | 37 |
Issue | ISSN | Citations |
5 | 0826-8185 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiaolu Hu | 1 | 0 | 0.34 |
Tingyao Jiang | 2 | 4 | 1.72 |
Min Wang | 3 | 76 | 27.77 |