Open AccessTopic Extraction of Online Curriculum Reviews
Author(s) -
Cheng Wang,
Ya Zhou
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2010/1/012077
Subject(s) - computer science , curriculum , artificial intelligence , stability (learning theory) , set (abstract data type) , sample (material) , machine learning , online learning , data set , data mining , multimedia , psychology , pedagogy , chemistry , chromatography , programming language
With the advent of the era of intelligent education, online learning has become a new way of learning. Online learning will produce a lot of review data, this paper focuses on how to correctly reflect learners’ emotional attitude towards the curriculum, this paper studies the mining of text topic emotion in MOOC course review data set. Firstly, the balanced algorithm is used for sample equalization, secondly, we use Albert + bilstm model to classify course reviews, finally, the LDA model is used to extract the corresponding topics. Compared with the experimental model, the proposed model has higher accuracy and stability. Machine learning method has some advantages, but the model is more complex, and it can be simplified in the future.