Extraction Method for Constructive Proposals based on Online Comments
Weipeng Cen, Zhigang Gao, Ruichao Xu, Bo Wu, Leilei Zheng, Wei Dong Zhao, Lei Xiao, Xuanzhang He · 2021 IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · 2021
In the flipped classroom teaching, it transfers the traditional teaching process from in-class to out-of-class, which is transforming the traditional education mode. In order to make good use of students' feedback data, and improve the quality of the online course and the effect of class teaching, this paper proposes an Extraction Method for constructive Proposals based on online Comments (EMPC). First, EMPC obtains the target words of course comments through BERT (Bidirectional Encoder Representations from Transformers) and the target filter algorithm, then it inputs target words into Bi-LSTM (Bi-directional Long Short-Term Memory) module with attention mechanism to obtain the opinion words. After all the target-opinion pairs are obtained, the algorithm based on k-means is used to extract constructive proposals. We conducted experiments by using MOOC (Massive Open Online Course) courses comment data, the experimental results show that EMPC achieves a high accuracy in both target word extraction and opinion word extraction, and it can get the proposals mentioned by students most frequently in order to improve the flipped classroom teaching.