Scholarlink

<p>We develop a model to infer the ideologies and influence of agents using social media. The novelty of our model is that it only requires a subset of connections in the network structure, where most models require the entire network structure and detailed socio-demographic characteristics of its agents. We apply the model to Twitter data to evaluate the social network between experts in the field of genome editing in livestock (GEL) and their followers. The model generates an ideological position score for each expert and follower, and their relative social influence. Estimates show that followers opposed to genome editing have more influence than those in favor, e.g., anti-GEL followers own 69% of the social influence in a typical conversation. A post hoc analysis shows that the projected consensus realized through interaction and learning is opposed to GEL. Our model can be used to infer positions, perceptions, and influences of social media users for any topic, and the empirical results can help inform investment, marketing, and policymaking decisions within the livestock industry.</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

Estimating ideology and influence in social media networks: opinions on genome editing of livestock

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月25日

查看全文
  • Joseph Navelski,
  • Syed Badruddoza,
  • Jill J. McCluskey,
  • Francis G. Pascual

摘要

We develop a model to infer the ideologies and influence of agents using social media. The novelty of our model is that it only requires a subset of connections in the network structure, where most models require the entire network structure and detailed socio-demographic characteristics of its agents. We apply the model to Twitter data to evaluate the social network between experts in the field of genome editing in livestock (GEL) and their followers. The model generates an ideological position score for each expert and follower, and their relative social influence. Estimates show that followers opposed to genome editing have more influence than those in favor, e.g., anti-GEL followers own 69% of the social influence in a typical conversation. A post hoc analysis shows that the projected consensus realized through interaction and learning is opposed to GEL. Our model can be used to infer positions, perceptions, and influences of social media users for any topic, and the empirical results can help inform investment, marketing, and policymaking decisions within the livestock industry.