首页|Research from National Center for Scientific Research (CNRS) Yields New Data on Applied Network Science (American politics in 3D: measuring multidimensional issue alignment in social media using social graphs and text data)
Research from National Center for Scientific Research (CNRS) Yields New Data on Applied Network Science (American politics in 3D: measuring multidimensional issue alignment in social media using social graphs and text data)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Network Daily News - A new study onapplied network science is now available. According to news reporting originating from the National Centerfor Scientific Research (CNRS) by NewsRx correspondents, research stated, “A growing number of socialmedia studies in the U.S. rely on the characterization of the opinion of individual users, for example, asDemocrat- or Republican-leaning, or in continuous scales ranging from most liberal to most conservative.”Funders for this research include Agence Nationale De La Recherche; Horizon 2020.The news editors obtained a quote from the research from National Center for Scientific Research(CNRS): “Recent works have shown, however, that additional opinion dimensions, for instance measuringattitudes towards elites, institutions, or cultural change, are also relevant for understanding socioinformationalphenomena on social platforms and in politics in general. The study of social networks inhigh-dimensional opinion spaces remains challenging in the US, both because of the relative dominance ofa principal liberal-conservative dimension in observed phenomena, and because two-party political systemsstructure both the preferences of users and the tools to measure them. This article leverages graph embeddingin multi-dimensional latent opinion spaces and text analysis to propose a method to identify additionalopinion dimensions linked to cultural, policy, social, and ideological groups and preferences. Using Twittersocial graph data we infer the political stance of nearly 2 million users connected to the political debate inthe U.S. for several issue dimensions of public debate. We show that it is possible to identify several newdimensions structuring social graphs, non-aligned with the classic liberal-conservative dimension. We alsoshow how the social graph is polarized to different degrees along these newfound dimensions, leveragingmulti-modality measures in opinion space.”
National Center for Scientific Research (CNRS)Applied Network SciencePoliticsScience
NETL
NSTL
