| Peer-Reviewed

Study of Association Rule Between College Students' Learning Behavior and Academic Records Based on Data Mining

Received: 6 March 2021     Accepted: 17 March 2021     Published: 26 March 2021
Views:       Downloads:
Abstract

The association rule between college students' daily behavior and school records has been the focus of education. Firstly, this paper summarizes the previous research results on this kind of problem, and studies many factors that affect college students' performance. Secondly, as an example of Institute of Disaster Prevention in China, the data of school records, online time and library time were extracted in this paper. The association between school records and the average daily online time, the average daily network flow and the time staying in library are discussed qualitatively via statistical analysis. It is pointed out that there is a negative correlation between daytime online time and academic records, and a positive correlation between library stay time and academic records. Then, using K-means clustering mining algorithm to analyze the online time and academic records, the results show that the excellent students spend less time online than the poor students, especially in the daytime. And using Apriori association analysis mining algorithm to study the relationship between the length of stay in Library and academic records. The minimum support and minimum credibility are set at 60%, and three strong association rules are obtained, that is, the students with good academic records stay in library for the longest time, the students with general academic records take the second place, and the students with poor academic records stay in library for the shortest time, which is completely consistent with the actual situation. This shows that the results of statistical method and data mining algorithm are consistent, that is, students who study well spend less time on Internet (shorter in the day) and more time in library than those with average records. The conclusion can help teachers to guide students to improve their achievement, so that students can better complete their studies, which has important guiding significance.

Published in American Journal of Education and Information Technology (Volume 5, Issue 1)
DOI 10.11648/j.ajeit.20210501.14
Page(s) 21-26
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2021. Published by Science Publishing Group

Keywords

Data Mining, Clustering Algorithm, Apriori Algorithm, Online Time, Library Time

References
[1] SHEN Hang-jie, JU Sheng-gen, SUN Jie-ping. Performance prediction based on fuzzy clustering and support vectorregression [J]. Journal of East China Normal University (Natural Science). 2019 (05): 66-73+84.
[2] LI Tiebo. Student Behavior Characteristics Analysis and Prediction Based on Campus Big Data [J]. Journal of Chongqing University of Technology (Natural Science). 2019, 33 (07): 201-206.
[3] CHEN Xi, MEI Guang, ZHANG Jinjin, XU Weisheng. Student grade prediction method based on knowledge graph and collaborative filtering [J]. Journal of Computer Application. 2020. 40 (2): 595-601.
[4] LI Zhong, AN Jianqin, LIU Haijun, SONG Yiyao. Association mining algorithm and its development trend [J]. Intelligent Computer and Applications. 2017. 7 (5): 22-25.
[5] YU Qinyang. Campus Big Data Based Analysis and Visualization of Students’ Abnormal Behaviors [D]. Beijing University of Technology. 2019.
[6] GU Jinchi. Analysis and prediction of influencing factors of student academic records based on multiple regression and decision tree model [J]. Management observation. 2019 (25): 156-157.
[7] WU Tangyan. The influence of students, school and family factors on the academic records of female college students [J]. Frontier. 2015 (11): 115-117.
[8] H Yao, D Lian, Y Cao, et al. Predicting Academic records for College Students [J]. Acm Transactions on Intelligent Systems & Technology. 2019. 10 (3): 1-21.
[9] ZHOU Qing, WANG Wei-fang, GE Liang, XIAO Yi-feng, TAI-Dai. Student Performance Prediction based on Campus Card Data and Curriculum Classification [J]. Computer Knowledge and Technology. 2018, 14 (24): 236-239.
[10] HE Hong, LIU Dongbo, ZHANG Bi. Correlation analysis between online learning behavior and student academic records on SPOC platform based on learning style classification [J]. Science and technology information. 2019. 3: 207-210.
[11] YANG Fang. A Research On Students' Borrowing Behavior in Local University Library Based on Data Mining - Take Ordos Institute of Technology as An Example [D]. Inner Mongolia University of science and technology. 2020.
[12] YANG Yi-fan, HE Guo-xian, LI Yong-ding, K-Means Algorithm for Optimizing Initial Cluster Center Selection [J]. Computer Knowledge and Technology. 2021.17 (5): 252-255.
[13] DONG Xuan-meng, GUO Li-wen, DONG Xian-wei, WANG Fu-sheng. Association Mining of Influencing Factors of Coal Spontaneous Combustion Based on Apriori Algorithm [J]. Journal of North China University of Science and Technology (Natural Science Edition). 2021.43 (1): 21-25.
[14] Huang Ke, Bi Chunguang, Wang Jinlong, Guo Hai, Yuan Shuai. Research on application of improved Apriori algorithm based on frequent itemsets in smart greenhouse [J]. Journal of Chinese Agricultural Mechanization, 2020, 41 (9): 182-189.
[15] HUANG Hui, ZENG Qingtao, TANG Mingjie, ZHANG Xiaoliang, Application of Student Achievement Analysis Based on Association Analysis [J]. Journal of Beijing Institute of Graphic Communication. 2021. 29 (2): 130-136.
Cite This Article
  • APA Style

    Zhong Li, Ying Li, Haiyang Li, Keke Sun. (2021). Study of Association Rule Between College Students' Learning Behavior and Academic Records Based on Data Mining. American Journal of Education and Information Technology, 5(1), 21-26. https://doi.org/10.11648/j.ajeit.20210501.14

    Copy | Download

    ACS Style

    Zhong Li; Ying Li; Haiyang Li; Keke Sun. Study of Association Rule Between College Students' Learning Behavior and Academic Records Based on Data Mining. Am. J. Educ. Inf. Technol. 2021, 5(1), 21-26. doi: 10.11648/j.ajeit.20210501.14

    Copy | Download

    AMA Style

    Zhong Li, Ying Li, Haiyang Li, Keke Sun. Study of Association Rule Between College Students' Learning Behavior and Academic Records Based on Data Mining. Am J Educ Inf Technol. 2021;5(1):21-26. doi: 10.11648/j.ajeit.20210501.14

    Copy | Download

  • @article{10.11648/j.ajeit.20210501.14,
      author = {Zhong Li and Ying Li and Haiyang Li and Keke Sun},
      title = {Study of Association Rule Between College Students' Learning Behavior and Academic Records Based on Data Mining},
      journal = {American Journal of Education and Information Technology},
      volume = {5},
      number = {1},
      pages = {21-26},
      doi = {10.11648/j.ajeit.20210501.14},
      url = {https://doi.org/10.11648/j.ajeit.20210501.14},
      eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajeit.20210501.14},
      abstract = {The association rule between college students' daily behavior and school records has been the focus of education. Firstly, this paper summarizes the previous research results on this kind of problem, and studies many factors that affect college students' performance. Secondly, as an example of Institute of Disaster Prevention in China, the data of school records, online time and library time were extracted in this paper. The association between school records and the average daily online time, the average daily network flow and the time staying in library are discussed qualitatively via statistical analysis. It is pointed out that there is a negative correlation between daytime online time and academic records, and a positive correlation between library stay time and academic records. Then, using K-means clustering mining algorithm to analyze the online time and academic records, the results show that the excellent students spend less time online than the poor students, especially in the daytime. And using Apriori association analysis mining algorithm to study the relationship between the length of stay in Library and academic records. The minimum support and minimum credibility are set at 60%, and three strong association rules are obtained, that is, the students with good academic records stay in library for the longest time, the students with general academic records take the second place, and the students with poor academic records stay in library for the shortest time, which is completely consistent with the actual situation. This shows that the results of statistical method and data mining algorithm are consistent, that is, students who study well spend less time on Internet (shorter in the day) and more time in library than those with average records. The conclusion can help teachers to guide students to improve their achievement, so that students can better complete their studies, which has important guiding significance.},
     year = {2021}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Study of Association Rule Between College Students' Learning Behavior and Academic Records Based on Data Mining
    AU  - Zhong Li
    AU  - Ying Li
    AU  - Haiyang Li
    AU  - Keke Sun
    Y1  - 2021/03/26
    PY  - 2021
    N1  - https://doi.org/10.11648/j.ajeit.20210501.14
    DO  - 10.11648/j.ajeit.20210501.14
    T2  - American Journal of Education and Information Technology
    JF  - American Journal of Education and Information Technology
    JO  - American Journal of Education and Information Technology
    SP  - 21
    EP  - 26
    PB  - Science Publishing Group
    SN  - 2994-712X
    UR  - https://doi.org/10.11648/j.ajeit.20210501.14
    AB  - The association rule between college students' daily behavior and school records has been the focus of education. Firstly, this paper summarizes the previous research results on this kind of problem, and studies many factors that affect college students' performance. Secondly, as an example of Institute of Disaster Prevention in China, the data of school records, online time and library time were extracted in this paper. The association between school records and the average daily online time, the average daily network flow and the time staying in library are discussed qualitatively via statistical analysis. It is pointed out that there is a negative correlation between daytime online time and academic records, and a positive correlation between library stay time and academic records. Then, using K-means clustering mining algorithm to analyze the online time and academic records, the results show that the excellent students spend less time online than the poor students, especially in the daytime. And using Apriori association analysis mining algorithm to study the relationship between the length of stay in Library and academic records. The minimum support and minimum credibility are set at 60%, and three strong association rules are obtained, that is, the students with good academic records stay in library for the longest time, the students with general academic records take the second place, and the students with poor academic records stay in library for the shortest time, which is completely consistent with the actual situation. This shows that the results of statistical method and data mining algorithm are consistent, that is, students who study well spend less time on Internet (shorter in the day) and more time in library than those with average records. The conclusion can help teachers to guide students to improve their achievement, so that students can better complete their studies, which has important guiding significance.
    VL  - 5
    IS  - 1
    ER  - 

    Copy | Download

Author Information
  • School of Emergency Management, Institute of Disaster Prevention, Langfang, China

  • School of Emergency Management, Institute of Disaster Prevention, Langfang, China

  • School of Emergency Management, Institute of Disaster Prevention, Langfang, China

  • School of Emergency Management, Institute of Disaster Prevention, Langfang, China

  • Sections