当前位置:
X-MOL 学术
›
Comput. Math. Organ. Theory
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Mining online communities to inform strategic messaging: practical methods to identify community-level insights
Computational and Mathematical Organization Theory ( IF 1.8 ) Pub Date : 2017-06-20 , DOI: 10.1007/s10588-017-9255-3 Matthew Benigni , Kenneth Joseph , Kathleen M. Carley
Computational and Mathematical Organization Theory ( IF 1.8 ) Pub Date : 2017-06-20 , DOI: 10.1007/s10588-017-9255-3 Matthew Benigni , Kenneth Joseph , Kathleen M. Carley
The ability of OSNs to propagate civil unrest has been powerfully observed through the rise of the ISIS and the ongoing conflict in Crimea. As a result, the ability to understand and in some cases mitigate the effects of user communities promoting civil unrest online has become an important area of research. Although methods to detect large online extremist communities have emerged in literature, the ability to summarize community content in meaningful ways remains an open research question. We introduce novel applications of the following methods: ideological user clustering with bipartite spectral graph partitioning, narrative mining with hash tag co-occurrence graph clustering, and identifying radicalization with directed URL sharing networks. In each case we describe how the method can be applied to social media. We subsequently apply them to online Twitter communities interested in the Syrian revolution and ongoing Crimean conflict.
中文翻译:
挖掘在线社区以提供战略消息:确定社区级见解的实用方法
通过ISIS的崛起和克里米亚的持续冲突,已强有力地观察到OSN传播内乱的能力。结果,理解并在某些情况下减轻用户社区在线促进内乱的影响的能力已成为重要的研究领域。尽管文献中已经出现了检测大型在线极端主义社区的方法,但是以有意义的方式总结社区内容的能力仍然是一个悬而未决的研究问题。我们介绍了以下方法的新颖应用:具有两方频谱图分区的思想用户聚类,具有哈希标签共现图聚类的叙事挖掘以及通过定向URL共享网络识别激进化。在每种情况下,我们都描述了该方法如何应用于社交媒体。
更新日期:2017-06-20
中文翻译:
挖掘在线社区以提供战略消息:确定社区级见解的实用方法
通过ISIS的崛起和克里米亚的持续冲突,已强有力地观察到OSN传播内乱的能力。结果,理解并在某些情况下减轻用户社区在线促进内乱的影响的能力已成为重要的研究领域。尽管文献中已经出现了检测大型在线极端主义社区的方法,但是以有意义的方式总结社区内容的能力仍然是一个悬而未决的研究问题。我们介绍了以下方法的新颖应用:具有两方频谱图分区的思想用户聚类,具有哈希标签共现图聚类的叙事挖掘以及通过定向URL共享网络识别激进化。在每种情况下,我们都描述了该方法如何应用于社交媒体。