Article: Evolution of cultural community interaction networks and information propagation based on dynamic interest graph Journal: International Journal of Information and Communication Technology (IJICT) 2026 Vol.27 No.59 pp.25 - 49 Abstract: This study addresses the inaccuracy of traditional static network models in predicting rapidly evolving interests within cultural communities by proposing an interactive network evolution model based on dynamic interest graphs. We find that members' shifting interests make information propagation paths unpredictable - for instance, trending topics in music communities may cycle as frequently as every two weeks. To tackle this challenge, we developed a graph model incorporating time-decay factors that captures real-time changes in interest similarity. Experiments demonstrate that compared to traditional static graph methods, our model achieves a 12.7% improvement in community structure prediction accuracy and reduces prediction error for information reach by 18.3%. This work offers new insights into understanding the dynamic evolution of cultural communities and enabling precise content dissemination. Inderscience Publishers - linking academia, business and industry through research

Title: Evolution of cultural community interaction networks and information propagation based on dynamic interest graph

Authors: Lu Wang

Addresses: School of Media and Design, Xi'an Peihua University, Xi'an, 710025, China

Abstract: This study addresses the inaccuracy of traditional static network models in predicting rapidly evolving interests within cultural communities by proposing an interactive network evolution model based on dynamic interest graphs. We find that members' shifting interests make information propagation paths unpredictable - for instance, trending topics in music communities may cycle as frequently as every two weeks. To tackle this challenge, we developed a graph model incorporating time-decay factors that captures real-time changes in interest similarity. Experiments demonstrate that compared to traditional static graph methods, our model achieves a 12.7% improvement in community structure prediction accuracy and reduces prediction error for information reach by 18.3%. This work offers new insights into understanding the dynamic evolution of cultural communities and enabling precise content dissemination.

Keywords: dynamic interest graph; cultural communities; network evolution; information dissemination.

DOI: 10.1504/IJICT.2026.153933

International Journal of Information and Communication Technology, 2026 Vol.27 No.59, pp.25 - 49

Received: 13 Feb 2026
Accepted: 21 Mar 2026
Published online: 08 Jun 2026 *

Title: Evolution of cultural community interaction networks and information propagation based on dynamic interest graph

Keep up-to-date