Analysis of Educational Big Data Mining Based on Deep Learning Technology

DOI

10.2991/ahis.k.220601.056How to use a DOI?

Keywords

Deep learning; Big data of education; Teaching assistance; data mining

Abstract

Behavioral data comes from a large database that collects data on students’ use of their campus smart cards. The main work of this paper includes: (1) firstly, this paper summarizes the research status of student behavior analysis and educational data mining technology at home and abroad, and further briefly introduces the basic algorithms and common classification algorithms of information education. By exploring the problems and importance of current student achievement prediction model modeling, this paper analyzes the related research and application of deep learning and sequence modeling. The subjectivity and difference of students’ behavior characteristics are described by statistical analysis method, which can not only understand the structure of data, but also better extract features and find out the potential practical value in behavior data. (2) Specifically, this paper uses the characteristics of campus behavior data to describe students’ learning behavior, life behavior and consumption behavior, and strive to establish a more comprehensive understanding of students’ traditional behavior mode, in order to improve the effect of performance prediction. In the use of the algorithm, it is not limited to a single algorithm, but selects a variety of algorithms to model students’ behavior on the basis of fully considering the data language characteristics, tests the advantages of different algorithms, and looks for the best multi classification prediction model.

Copyright

© 2022 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license.

Download article (PDF)

TY  - CONF
AU  - Jianwu He
PY  - 2022
DA  - 2022/06/02
TI  - Analysis of Educational Big Data Mining Based on Deep Learning Technology
BT  - Proceedings of the 2021 International conference on Smart Technologies and Systems for Internet of Things (STS-IOT 2021)
PB  - Atlantis Press
SP  - 299
EP  - 304
SN  - 2589-4919
UR  - https://doi.org/10.2991/ahis.k.220601.056
DO  - 10.2991/ahis.k.220601.056
ID  - He2022
ER  -