Proceedings of the 2019 International Conference on Advanced Education Research and Modern Teaching (AERMT 2019)

Research on College Class Style Evaluation Based on Big Data

Authors
Yanfei Chen, Chunying Huang, Xinhong Chen, Guitian Liu, Zhiwei Zheng, Ruijia Liu, Xiaohua Li
Corresponding Author
Xiaohua Li
Available Online October 2019.
DOI
https://doi.org/10.2991/aermt-19.2019.24How to use a DOI?
Keywords
big data, class style evaluation, entropy weight method, factor analysis
Abstract
Class style is an important indicator affecting the quality of talent training in colleges and universities. How to establish an effective class style evaluation model is of great significance to promote the formation of excellent class style and provide decision support for university personnel training programs. Compared with previous studies, this paper comprehensively considers the factors affecting the evaluation based on the principle of combining subjectivity with objectivity. With the changes of higher education reform, we have prospectively incorporated the indicators that may reflect the status of the work style into the evaluation system. On the basis of these innovative principles, this paper realized low-cost data collection with digital campus, and combined entropy weight method, high-order factor analysis method and similarity cosine calculation method to build a class evaluation analysis model based on big data.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Cite this article

TY  - CONF
AU  - Yanfei Chen
AU  - Chunying Huang
AU  - Xinhong Chen
AU  - Guitian Liu
AU  - Zhiwei Zheng
AU  - Ruijia Liu
AU  - Xiaohua Li
PY  - 2019/10
DA  - 2019/10
TI  - Research on College Class Style Evaluation Based on Big Data
BT  - Proceedings of the 2019 International Conference on Advanced Education Research and Modern Teaching (AERMT 2019)
PB  - Atlantis Press
SP  - 99
EP  - 102
SN  - 2352-5398
UR  - https://doi.org/10.2991/aermt-19.2019.24
DO  - https://doi.org/10.2991/aermt-19.2019.24
ID  - Chen2019/10
ER  -