TEVISE：一个探索推文数据中关键词关系演变的交互式可视化分析工具
TEVISE: An Interactive Visual Analytics Tool to Explore Evolution of Keywords' Relations in Tweet Data
摘要：
最近，TExVis工具通过可视化频繁关键字之间的关系打开了一个新的窗口来探索推文数据。然而，对tweet数据的时间轴探索，在TExVis中不存在，可以在理解人们的反馈和反应随时间的变化方面发挥关键作用。针对这一点，我们提出了我们的可视化分析工具，称为TEVisE。它使用增强的邻接矩阵图来克服TExVis中的混乱问题，并可视化频繁关键字的演变以及这些关键字之间的关系。我们进行了两个用户研究，以找到我们的两个制定的研究问题的答案。在第一个用户研究中，我们专注于从通用可用性度量和认知负荷理论的角度评估两个工具中使用的可视化布局。我们发现TEVisE工具在与阅读相关的任务中具有更好的准确性，探索频繁关键词之间的关系。在第二项研究中，我们收集了用户对探索TEVisE中的摘要视图和新的时间轴演变视图的反馈。在第二项研究中，我们收集了用户对探索TEVisE中的摘要视图和新的时间轴演变视图的反馈。我们发现，参与者更喜欢这两种观点，一种是为了得到整体的一瞥，而另一种是为了得到随着时间的推移而变化的趋势。
英文摘要：
Recently, a new window to explore tweet data has been opened in TExVis tool through visualizing the relations between the frequent keywords. However, timeline exploration of tweet data, not present in TExVis, could play a critical factor in understanding the changes in people's feedback and reaction over time. Targeting this, we present our visual analytics tool, called TEVisE. It uses an enhanced adjacency matrix diagram to overcome the cluttering problem in TExVis and visualizes the evolution of frequent keywords and the relations between these keywords over time. We conducted two user studies to find answers of our two formulated research questions. In the first user study, we focused on evaluating the used visualization layouts in both tools from the perspectives of common usability metrics and cognitive load theory. We found better accuracy in our TEVisE tool for tasks related to reading exploring relations between frequent keywords. In the second study, we collected users' feedback towards exploring the summary view and the new timeline evolution view inside TEVisE. In the second study, we collected users' feedback towards exploring the summary view and the new timeline evolution view inside TEVisE. We found that participants preferred both view, one to get overall glance while the other to get the trends changes over time.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
