Istituto dei Sistemi Complessi (ISC)-CNR, UOS Sapienza, Rome, Italy.
IMT School for Advanced Studies, Lucca, Italy.
PLoS One. 2019 Jan 28;14(1):e0211038. doi: 10.1371/journal.pone.0211038. eCollection 2019.
The advent of social networks revolutionized the way people access to information sources. Understanding the complex relationship between these sources and users is crucial. We introduce an algorithm, that we call PopRank, to assess both the Impact of Facebook pages as well as users' Engagement on the basis of their mutual interactions. The ideas behind the PopRank are that i) high impact pages attract many users with a low engagement, which means that they receive comments from users that rarely comment, and ii) high engagement users interact with high impact pages, that is they mostly comment pages with a high popularity. The resulting ranking of pages can predict the number of comments a page will receive and the number of its future posts. Pages' impact turns out to be slightly dependent on the quality of pages' informative content (e.g., science vs conspiracy) but independent of users' polarization.
社交网络的出现彻底改变了人们获取信息来源的方式。理解这些来源和用户之间的复杂关系至关重要。我们引入了一种算法,称为 PopRank,用于根据它们的相互作用评估 Facebook 页面的影响力以及用户的参与度。PopRank 的理念是:i)高影响力的页面吸引了许多低参与度的用户,这意味着它们收到了很少发表评论的用户的评论;ii)高参与度的用户与高影响力的页面互动,也就是说,他们主要评论高人气的页面。由此产生的页面排名可以预测页面将收到的评论数量和未来发布的帖子数量。页面的影响力与页面信息内容的质量(例如,科学与阴谋)略有相关,但与用户的两极分化无关。