Visualization Study on the Transmission Path of Ideological and Political Discourse Influence on Social Media Platforms

Abstract

The dissemination of ideological and political discourse on social media platforms often suffers from hidden propagation routes and unquantifiable influence effects. This paper constructs a visualization analysis framework based on multi-source data perception and dynamic graph inference. First, multimodal data from social media platforms are collected, including topic tags, user interaction relationships, text, images, and video comments. A BERT-based model is used for sentiment mining and key node identification. Second, social network analysis and temporal hypergraph modeling are integrated to quantify discourse dissemination paths at macro-network, meso-community, and micro-information-diffusion levels. Third, an interactive dynamic influence graph is built using ECharts and D3.js to present node structure, emotional tendency, community evolution, and propagation trees. Empirical results show that the proposed method achieves an F1 score of 0.914 in path reconstruction, and the correlation coefficient between sentiment quantification and expert ratings exceeds 0.89. The framework effectively reveals the black-box characteristics of discourse dissemination and provides data support for precise ideological and political communication guidance.