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

<p>This paper explores the process of patriotism knowledge mapping from three aspects: graph entropy definition, entropy2vec and topic knowledge, and constructs the overall framework of patriotism knowledge mapping. The multivariate information technology in the era of all media is used to summarize the educational knowledge of the patriotism theme, construct the entity-relationship extraction model based on the Bi-LSTM network, and propose the SFAJED fusion algorithm to carry out the knowledge fusion of the patriotism education theme. After exploring the relationship extraction effect, knowledge fusion effect, and overall effect of the constructed knowledge graph, the timeliness of patriotism education for college students is analyzed. The results show that the network density of the constructed patriotism knowledge map is concentrated at about 0.004, the aggregation coefficient is concentrated at about 0.45, and the average road strength length of the graph is about 20. It is divided into three stages in accordance with the time axis: 2015~2017 is the patriotism education with class as the main axis, 2017~2018 is the patriotism education with the country as the basis, and 2018~2020 is the patriotism education with the culture as the virtue, and at this time, the strength is respectively between 2.3~3.5, between 2.12~3.08 and between 1.08~2.88.</p>
</abstract>

This paper explores the process of patriotism knowledge mapping from three aspects: graph entropy definition, entropy2vec and topic knowledge, and constructs the overall framework of patriotism knowledge mapping. The multivariate information technology in the era of all media is used to summarize the educational knowledge of the patriotism theme, construct the entity-relationship extraction model based on the Bi-LSTM network, and propose the SFAJED fusion algorithm to carry out the knowledge fusion of the patriotism education theme. After exploring the relationship extraction effect, knowledge fusion effect, and overall effect of the constructed knowledge graph, the timeliness of patriotism education for college students is analyzed. The results show that the network density of the constructed patriotism knowledge map is concentrated at about 0.004, the aggregation coefficient is concentrated at about 0.45, and the average road strength length of the graph is about 20. It is divided into three stages in accordance with the time axis: 2015~2017 is the patriotism education with class as the main axis, 2017~2018 is the patriotism education with the country as the basis, and 2018~2020 is the patriotism education with the culture as the virtue, and at this time, the strength is respectively between 2.3~3.5, between 2.12~3.08 and between 1.08~2.88.

Analysis of the timeliness of multiple information on college students’ patriotism education in the all-media era

Applied Mathematics and Nonlinear Sciences

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

This paper explores the process of patriotism knowledge mapping from three aspects: graph entropy definition, entropy2vec and topic knowledge, and constructs...

Analysis of the timeliness of multiple information on college students’ patriotism education in the all-media era

Publié en ligne: 23 déc. 2023

Pages: -

Reçu: 19 janv. 2023

Accepté: 03 juil. 2023

DOI: https://doi.org/10.2478/amns.2023.2.01596

Mots clés
Knowledge graph, Multiple information, Bi-LSTM, SFAJED algorithm, Patriotism education

© 2023 Ying Meng, published by Sciendo

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

Analysis of the timeliness of multiple information on college students’ patriotism education in the all-media era

Publié en ligne: 23 déc. 2023

Pages: -

Reçu: 19 janv. 2023

Accepté: 03 juil. 2023

DOI: https://doi.org/10.2478/amns.2023.2.01596

Mots clésKnowledge graph, Multiple information, Bi-LSTM, SFAJED algorithm, Patriotism education

© 2023 Ying Meng, published by Sciendo

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

Mots clés
Knowledge graph, Multiple information, Bi-LSTM, SFAJED algorithm, Patriotism education