Title: Prediction method for the dissemination popularity of social network news information based on grey model

Authors: Baoyu Huang

Addresses: School of Information Engineering, Xiamen Ocean Vocational College, Xiamen, Fujian, China

Abstract: A grey model-based method for predicting the popularity of social network news information dissemination is proposed with the aim of improving the accuracy of turning point prediction and reducing quantile bias. Firstly, the social network news information data is transformed into a text network form, and semantic features are extracted based on the dependency of nodes on edges and the importance of nodes themselves in the text network. Then, utilising cross attention mechanism to achieve intelligent fusion of feature features. Finally, based on the grey Verhulst model, predict the popularity of news information dissemination and divide the popularity range. The experimental results show that the quantile deviation of the predicted results by this method ranges from 0.206% to 0.258%, and the minimum accuracy of turning point prediction is 0.90, and the maximum accuracy can reach 0.96.

Keywords: social networks; news information; information dissemination; grey Verhulst model; heat prediction.

DOI: 10.1504/IJIPT.2024.146274

International Journal of Internet Protocol Technology, 2024 Vol.17 No.4, pp.211 - 219

Received: 12 Feb 2025
Accepted: 30 Mar 2025
Published online: 14 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article