Data sets from Carrizosa, Guerrero, Hardt and Romero Morales (2017) "On Building Online Dynamic Visualization Maps for News Data Streams" (article/paper under submission)

In this paper we develop an online tool to visualize news data over a time horizon. First, we perform a Natural Language Processing analysis, where the words are extracted, and their attributes, namely the importance and the relatedness, are calculated. Second, we present a Mathematical Optimization model for the visualization problem and a numerical optimization approach. The model represents the words using circles, whose time-varying area displays the importance of the word in each time period. The location of the words in the visualization region is guided by three criteria, namely, the accurate representation of the relatedness, the spread of the words in the visualization region to improve the quality of the visualization, as well as the visual stability over the time horizon. Our approach is flexible, allows user interaction and is scalable. We show results for three case studies using data from Danish news sources.

本研究开发了一款可针对时间跨度内的新闻数据进行可视化的在线工具。首先，我们实施了自然语言处理（Natural Language Processing）分析，提取文本词汇并计算其两项核心属性：重要性与相关性。其次，我们针对该可视化问题提出了数学优化（Mathematical Optimization）模型与数值优化求解方法。该模型以圆形表征词汇，圆形随时间变化的面积可展示该词汇在各时间段内的重要程度。词汇在可视化区域内的布局遵循三项准则：精准呈现词汇间的相关性、使词汇在可视化区域内均匀分布以提升可视化质量，以及维持时间跨度内的视觉稳定性。本方法具备灵活性，支持用户交互且可扩展性良好。我们采用丹麦新闻源数据开展了三项案例研究，并展示了对应的实验结果。