<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>This paper first describes the parallel association rule mining method for the big data implementation process. To perform similar item merging, each data item in the dataset is scanned, the dataset is divided, and then the similarity degree is calculated. And the dynamic support threshold is obtained based on the idea of genetic iteration of the genetic algorithm to obtain the optimal solution. In order to conduct data mining, the mining process is then transferred to the MapReduce computing platform while the data output from the Map step is parallel LZO compressed. Finally, in the age of big data, the ideological and political work in colleges is mined and analyzed using a data mining algorithm, and route innovation remedies are proposed. According to the current state of ideological and political education, 77.6% of respondents believe that the ideological and political management system is not ideal, and 61.48 percent believe that the ideological and political content is fragmented and that data-based information makes it challenging to supervise. The immaturity of new media development and the growth of technological challenges amounted to 46%. After creative approaches, ideological and political education teaching satisfaction has grown by 15-20 percentage points. Ideological and political education at universities under the impact of big data should grab the possibilities and overcome the difficulties to achieve sustainability and innovative development.</p>
</abstract>

This paper first describes the parallel association rule mining method for the big data implementation process. To perform similar item merging, each data item in the dataset is scanned, the dataset is divided, and then the similarity degree is calculated. And the dynamic support threshold is obtained based on the idea of genetic iteration of the genetic algorithm to obtain the optimal solution. In order to conduct data mining, the mining process is then transferred to the MapReduce computing platform while the data output from the Map step is parallel LZO compressed. Finally, in the age of big data, the ideological and political work in colleges is mined and analyzed using a data mining algorithm, and route innovation remedies are proposed. According to the current state of ideological and political education, 77.6% of respondents believe that the ideological and political management system is not ideal, and 61.48 percent believe that the ideological and political content is fragmented and that data-based information makes it challenging to supervise. The immaturity of new media development and the growth of technological challenges amounted to 46%. After creative approaches, ideological and political education teaching satisfaction has grown by 15-20 percentage points. Ideological and political education at universities under the impact of big data should grab the possibilities and overcome the difficulties to achieve sustainability and innovative development.

Research on the innovation of the path of ideological and political education in universities based on data mining

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

This paper first describes the parallel association rule mining method for the big data implementation process. To perform similar item merging, each data item...

Research on the innovation of the path of ideological and political education in universities based on data mining

Online veröffentlicht: 02. Okt. 2023

Seitenbereich: -

Eingereicht: 18. Okt. 2022

Akzeptiert: 12. Apr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00440

Schlüsselwörter
Genetic iteration, Ideology and politics, Dynamic support threshold, Association rules, Data mining

© 2023 Suyu Rao, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Research on the innovation of the path of ideological and political education in universities based on data mining

Online veröffentlicht: 02. Okt. 2023

Seitenbereich: -

Eingereicht: 18. Okt. 2022

Akzeptiert: 12. Apr. 2023

DOI: https://doi.org/10.2478/amns.2023.2.00440

SchlüsselwörterGenetic iteration, Ideology and politics, Dynamic support threshold, Association rules, Data mining

© 2023 Suyu Rao, published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Genetic iteration, Ideology and politics, Dynamic support threshold, Association rules, Data mining