Feng Zhuowen, Xing Yuru, Wang Guancheng
College of Literature and News Communication, Guangdong Ocean University, ZhanJiang, 524088, China.
College of Electronic and Information Engineering, Guangdong Ocean University, ZhanJiang, 524088, China.
Sci Rep. 2024 Dec 28;14(1):30883. doi: 10.1038/s41598-024-81857-2.
In the context of social networks becoming primary platforms for information dissemination and public discourse, understanding how opinions compete and reach consensus has become increasingly vital. This paper introduces a novel distributed competition model designed to elucidate the dynamics of opinion competitive behavior in social networks. The proposed model captures the development mechanism of various opinions, their appeal to individuals, and the impact of the social environment on their evolution. The model reveals that a subset of opinions ultimately prevails and is adopted. Key elements of social networks are quantified as parameters, with parameter variations representing the dynamics of opinions. Furthermore, a modified gradient-based neural network is designed as the evolutional law of the opinion, whose stability and convergence are confirmed by theoretical analysis. Additionally, experiments simulate real-world competitive scenarios, demonstrating practical applications for the model. This model can be widely applied to various filed in social networks, offering a new perspective for understanding and predicting competition phenomenon in complex social systems. Overall, this work provides a structured and systematic approach to understanding opinion dynamics, which greatly enhances our ability to analyze competitive behaviors and anticipate the outcomes of diverse viewpoints in social networks.
在社交网络成为信息传播和公众话语的主要平台的背景下，理解观点如何竞争并达成共识变得越来越重要。本文介绍了一种新颖的分布式竞争模型，旨在阐明社交网络中观点竞争行为的动态变化。所提出的模型捕捉了各种观点的发展机制、它们对个体的吸引力以及社会环境对其演变的影响。该模型表明，一部分观点最终会占上风并被采纳。社交网络的关键要素被量化为参数，参数的变化代表观点的动态变化。此外，设计了一种基于梯度的改进神经网络作为观点的演化规律，通过理论分析证实了其稳定性和收敛性。此外，实验模拟了现实世界中的竞争场景，展示了该模型的实际应用。该模型可广泛应用于社交网络的各个领域，为理解和预测复杂社会系统中的竞争现象提供了新的视角。总体而言，这项工作提供了一种结构化、系统化的方法来理解观点动态，极大地增强了我们分析社交网络中竞争行为和预测不同观点结果的能力。
