摘要
旭日图是一种现代饼图,它超越传统的饼图和环图,不仅能表达数据的占比问题,更能表达清晰的层级和归属关系,以父子层次结构来显示数据的构成情况。使用传统的旭日图对文本数据进行可视化时,不能全面地展示实体关系和情感偏向,而且旭日图层数越多,信息的可读性就越低。针对以上问题,对传统的旭日图进行了改进。首先,设计同级相邻圆弧的交叠,展示文本中实体的关系。然后,将旭日图与柱形图相结合,展示评论文本的感情偏向,柱形图体现为圆弧的涂色宽度,表示对于某方面评论的满意度。最后,对数据进行优化重排,包括:1)基于整体的考虑,将凸出部分放在邻接位置以节省空间;2)对局部的数据优化进行重排,使得最外层的节点尽可能高低错落,以提高稀疏性,便于观察。实验结果表明:改进的旭日图能够更全面、清晰地对评论文本进行可视化,为用户提供更灵活、个性化的可视化展示。
Sunburst is a kind of modern pie chart.It goes beyond the traditional pie chart and ring chart.It can not only express the proportion of data,but also express the clear hierarchy and attribution relationship,and display the data composition with the hierarchical structure of father and son.When Sunburst is used to visualize text data,it can not fully display the entity relationship and emotional bias.In addition,the more hierarchies of the Sunburst is involved,the lower readability of the information will be.In view of the above problems,this paper proposed the following improvements to the traditional Sunburst.Firstly,the overlapping of the same level adjacent arc is designed to show the relation of the entity in the text.Sencondly,the combination of Sunburst and histogram is put forward to show the emotional bias of the comment text.The color width of the arc in histogram chart expresses the satisfaction of the comment on a certain aspect.Thirdly,the data are rearranged optimally,including that for the overall consideration,the protruding part is placed in the adjacent position to save space,and the local data is optimized and rearranged to make the outermost nodes as high and low as possible,so as to improve the sparsity and facilitate observation.The experimental results show that the improved Sunburst can provide more comprehensive and clear visualization of comment text,and provide more flexible and personalized visualization display for users.
作者
易小群
李天瑞
陈超
YI Xiao-qun;LI Tian-rui;CHEN Chao(School of Information Science and Technology,Southwest Jiaotong University,Chengdu 611756,China;Institute of Artificial Intelligence,Southwest Jiaotong University,Chengdu 611756,China;National Engineering Laboratory of Integrated Transportation Big Data Application Technology, Southwest Jiaotong University,Chengdu 611756,China)
出处
《计算机科学》
CSCD
北大核心
2019年第10期14-18,共5页
Computer Science
基金
国家自然科学基金(61573292)资助
关键词
可视化
旭日图
情感偏向
数据重排
交互
Visualization
Sunburst
Emotive tendency
Data rearrangement
Interaction