Analyzing the Dynamics of National Cohesion in Persian-Language Social Media: A Topological Study Using Graph Neural Networks (GNNs) during the Iran–Israel War

Q: How can I download an article?

To download an article from SID, first log in to the site, search for the article title, and click on the 'Download Article' option.

Q: How can I download an ISI article?

To download an ISI article on SID, enter the keyword or article title in the search bar, view the relevant results, click on the desired article, and select the 'Download Article' option.

Q: How can I access the SID database?

To access the SID database, visit SID.ir, create an account, and log in to access scientific resources.

Q: Is downloading articles from SID free?

Some articles on SID are available for free, while others require payment. Details are specified on the article's page.

Zarghami Mohammad Hossein

مرکز اطلاعات علمی Scientific Information Database (SID) - Trusted Source for Research and Academic Resources

Journal Paper

Paper Information

Journal: JOURNAL OF MILITARY MEDICINE Year:2025 | Volume:27 | Issue:ویژه نامه شماره 1 Page(s): 37-47

Download Full-Text

Persian Verion

View:

Download:

Cites:

Information Journal Paper

Title

Analyzing the Dynamics of National Cohesion in Persian-Language Social Media: A Topological Study Using Graph Neural Networks (GNNs) during the Iran–Israel War

Author(s)

Zarghami Mohammad Hossein | Issue Writer Certificate

Keywords

War

National Cohesion

Social Networks

Graph Neural Networks (GNN)

Abstract

Background and Aim: This study examines the dynamics of national cohesion in Persian-speaking cyberspace during the Iran-Israel war. The main objective was to analyze how the structure of discursive networks changed and the degree of convergence of users in critical situations in order to determine how national cohesion is formed in digital platforms and what its characteristics are. Methods: To achieve this goal, data from the two platforms Twitter and Instagram, including more than 112, 000 interactions from 11, 000 active users, were extracted. Structural changes in discursive networks in three time periods-before the war, during the war, and after it-were modeled and explained using Temporal Graph Neural Networks (T-GNN). Network topological indices (density, clustering coefficient, degree centrality, modularity) and content analysis including sentiments and discourse themes were examined. Results: The results showed that the war as a “catalytic event” caused a significant increase in network density (+78. 3%), clustering coefficient (+131. 5%), and degree centrality (+82. 9%) along with, a decrease in modularity (–34. 4%), which indicates temporary and reactive cohesion in accordance with the “gathering around the flag” theory. However, after the war (until 25 September 1404), the network structure did not return to its initial state and still had a significant difference from the pre-war conditions. The T-GCN model was able to predict topological changes and community stability with high accuracy (R² > 0. 83 and AUC-ROC = 0. 88). Also, the analysis of network indices showed that “betweenness centrality” (0. 234) and “content sentiment” (0. 189) play a key role in shaping war cohesion. The content sentiment analysis also showed a significant increase in positive content (67. 3%) with themes such as “national unity”, “defending the homeland” and “supporting the armed forces” at the height of the war, while themes related to “peace” and “diplomacy” became more prominent after the war. Conclusion: These findings indicate that national cohesion in digital platforms is dynamic, transient, and somewhat fragile in nature. Although it is rapidly reproduced in crisis situations, its long-term sustainability requires going beyond emotional cohesion. From a methodological perspective, this study shows that combining topological and content analysis using Graph Neural Networks (GNNs) can provide a new framework for understanding the complexities of collective identity and national cohesion in the digital age.

Multimedia

No record.

Cites

No record.

References

No record.

Cite

Related Journal Papers

No record.

Related Seminar Papers

No record.

Related Plans