Abstract：
Literature on social networks and elections has focused on predicting electoral outcomes rather than on understanding how the discussions between users evolve over time. As a result, most studies focus on a single election and few comparative studies exist. In this article, a framework to analyze Twitter conversations about the election candidates is proposed. Using DeGroot\'s consensus model (an assumption that all users are attempting to persuade others to talk about a candidate), this framework is useful to identify the structure and strength of connections of the mention networks on the months before an election day. It also helps to make comparisons between elections and identify patterns in different contexts. In concrete, it was found that elections in which the incumbent was running have slower convergence (more closed communities with fewer links between them) and that there is no difference between parliamentary and presidential elections. Therefore, there is evidence that the political system and the role of the incumbent in the election influences the way conversations on Twitter occur.
摘要：
关于社交网络和选举的文献侧重于预测选举结果，而不是理解用户之间的讨论如何随着时间的推移而演变。因此,大多数研究都集中在一次选举上，很少有比较研究存在。在这篇文章中,提出了一个框架来分析Twitter关于选举候选人的谈话。使用DeGroot的共识模型（假设所有用户都试图说服其他人谈论候选人），该框架有助于确定选举日前几个月提及网络的结构和连接强度。它还有助于在选举之间进行比较，并确定不同背景下的模式。具体而言，人们发现，现任总统竞选的选举趋同较慢(更封闭的社区，它们之间的联系更少)，议会和总统选举之间没有区别。因此,有证据表明，政治制度和现任总统在选举中的作用会影响Twitter上对话的发生方式。
