Scholarlink

<p>In social media networks, information dissemination is characterized by intricate dynamics, yet the phenomenon of textual information mutation arising from individuals’ cognitive interpretations and emotional predispositions remains underexplored. Particularly in contexts of information variation, optimizing effective information diffusion represents a critical scientific challenge demanding rigorous investigation. To address the challenge of influence maximization under information variation, this study proposes a novel information dissemination model with semantic similarity measurement and sentiment analysis. We conceptualize textual information as vector representations and develop a sophisticated matching function to quantify inter-vector semantic distances. During the dissemination process, information diffusion is regulated by two complementary mechanisms: (1) a similarity-based threshold approach identifying effectively influenced recipients, and (2) an emotional intensity assessment for marginal nodes. A greedy selection algorithm is strategically deployed to maximize the reach and effectiveness of information diffusion. The proposed model undergoes comprehensive validation using real-world social network datasets, yielding empirically grounded insights into information diffusion dynamics. Our theoretical framework and methodology provide nuanced perspectives on optimizing communication strategies in complex digital ecosystems.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Decoding digital whispers: a semantic–emotional variation model of information diffusion in social media networks

  • 期刊论文

  • 发表日期：

    2026年5月31日

查看全文
  • Donghui Yang,
  • Yongbo Ni,
  • Jingyu Wang,
  • Zenglei Yue,
  • Xue Wu,
  • Mingyang Zhang

摘要

In social media networks, information dissemination is characterized by intricate dynamics, yet the phenomenon of textual information mutation arising from individuals’ cognitive interpretations and emotional predispositions remains underexplored. Particularly in contexts of information variation, optimizing effective information diffusion represents a critical scientific challenge demanding rigorous investigation. To address the challenge of influence maximization under information variation, this study proposes a novel information dissemination model with semantic similarity measurement and sentiment analysis. We conceptualize textual information as vector representations and develop a sophisticated matching function to quantify inter-vector semantic distances. During the dissemination process, information diffusion is regulated by two complementary mechanisms: (1) a similarity-based threshold approach identifying effectively influenced recipients, and (2) an emotional intensity assessment for marginal nodes. A greedy selection algorithm is strategically deployed to maximize the reach and effectiveness of information diffusion. The proposed model undergoes comprehensive validation using real-world social network datasets, yielding empirically grounded insights into information diffusion dynamics. Our theoretical framework and methodology provide nuanced perspectives on optimizing communication strategies in complex digital ecosystems.