Premium
Adaptive recommendation for MOOC with collaborative filtering and time series
Author(s) -
Pang Yanxia,
Liu Wenyan,
Jin Yuanyuan,
Peng Hongwei,
Xia Tian,
Wu Yonghe
Publication year - 2018
Publication title -
computer applications in engineering education
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.478
H-Index - 29
eISSN - 1099-0542
pISSN - 1061-3773
DOI - 10.1002/cae.21995
Subject(s) - loneliness , dropout (neural networks) , computer science , collaborative filtering , process (computing) , recommender system , feature (linguistics) , feeling , point (geometry) , multimedia , series (stratigraphy) , artificial intelligence , world wide web , machine learning , psychology , social psychology , paleontology , linguistics , philosophy , geometry , mathematics , psychiatry , biology , operating system
Massive Open Online Course (MOOC) has developed rapidly in recent years. However, the low satisfaction and the feelings of loneliness tend to cause more dropouts. A solution called Adaptive Recommendation for MOOC (ARM) is proposed aiming at the problem. Traditional MOOC recommendations are usually on the feature of interest. Among the recorded MOOC data, new recommendation features are selected for better balance on satisfaction. ARM trades off features adaptively according to the learner's requirement of satisfaction. Collaborative Filtering provides explicit information of similar learners and supports Collaborative Learning for less loneliness. ARM creatively combines Collaborative Filtering and time series to improve the recommendation accuracy. Specifically, Hawkes point process is improved to model the motivate and demotivate effect of score for future learning. Experiments with real‐world data show the accuracy of the ARM in recommendations and improvements in the dropout rate.