TY - JOUR
T1 - Top-N personalized recommendation with graph neural networks in MOOCs
AU - Wang, Jingjing
AU - Xie, Haoran
AU - Wang, Fu Lee
AU - Lee, Lap Kei
AU - Au, Oliver Tat Sheung
N1 - Publisher Copyright:
© 2021 The Authors
PY - 2021/1
Y1 - 2021/1
N2 - Top-N personalized recommendation has been extensively studied in assisting learners in finding interesting courses in MOOCs. Although existing Top-N personalized recommendation methods have achieved comparable performance, these models have two major shortcomings. First, these models seldom learn an explicit representation of the structural relation of items. Second, most of these models typically obtain a user's general preference and neglect the recency of items. This paper proposes a Top-N personalized Recommendation with Graph Neural Network (TP-GNN) in the Massive Open Online Course (MOOCs) as a solution to tackle this problem. We explore two different aggregate functions to deal with the user's sequence neighbors and then use an attention mechanism to generate the final item representations. The experiments on a real-world course dataset demonstrated that TP-GNN could improve the performances. Furthermore, the system developed based on our method obtains positive feedback from the participants, which denotes that our method effectively predicts learners’ preferences and needs.
AB - Top-N personalized recommendation has been extensively studied in assisting learners in finding interesting courses in MOOCs. Although existing Top-N personalized recommendation methods have achieved comparable performance, these models have two major shortcomings. First, these models seldom learn an explicit representation of the structural relation of items. Second, most of these models typically obtain a user's general preference and neglect the recency of items. This paper proposes a Top-N personalized Recommendation with Graph Neural Network (TP-GNN) in the Massive Open Online Course (MOOCs) as a solution to tackle this problem. We explore two different aggregate functions to deal with the user's sequence neighbors and then use an attention mechanism to generate the final item representations. The experiments on a real-world course dataset demonstrated that TP-GNN could improve the performances. Furthermore, the system developed based on our method obtains positive feedback from the participants, which denotes that our method effectively predicts learners’ preferences and needs.
KW - Graph neural networks
KW - MOOCs
KW - Personalized learning
KW - Recommender Systems
UR - http://www.scopus.com/inward/record.url?scp=85120404975&partnerID=8YFLogxK
U2 - 10.1016/j.caeai.2021.100010
DO - 10.1016/j.caeai.2021.100010
M3 - Article
AN - SCOPUS:85120404975
VL - 2
JO - Computers and Education: Artificial Intelligence
JF - Computers and Education: Artificial Intelligence
M1 - 100010
ER -