期刊
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS
卷 28, 期 1, 页码 346-356出版社
IEEE COMPUTER SOC
DOI: 10.1109/TVCG.2021.3114814
关键词
Data visualization; Visualization; Machine learning algorithms; Approximation algorithms; Task analysis; Encoding; Clustering algorithms; Visualization Tools; Visualization Recommendation Algorithms
资金
- NSF [IIS-1850115]
- Adobe Research Award
- National Research Foundation of Korea [4120200913638] Funding Source: Korea Institute of Science & Technology Information (KISTI), National Science & Technology Information Service (NTIS)
This paper proposes an evaluation-focused framework for contextualizing and comparing visualization recommendation algorithms. It analyzes algorithmic performance through theoretical and empirical comparisons, suggesting the need for more rigorous formal comparisons to clarify the benefits of recommendation algorithms in different analysis scenarios.
Although we have seen a proliferation of algorithms for recommending visualizations, these algorithms are rarely compared with one another, making it difficult to ascertain which algorithm is best for a given visual analysis scenario. Though several formal frameworks have been proposed in response, we believe this issue persists because visualization recommendation algorithms are inadequately specified from an evaluation perspective. In this paper, we propose an evaluation-focused framework to contextualize and compare a broad range of visualization recommendation algorithms. We present the structure of our framework, where algorithms are specified using three components: (1) a graph representing the full space of possible visualization designs, (2) the method used to traverse the graph for potential candidates for recommendation, and (3) an oracle used to rank candidate designs. To demonstrate how our framework guides the formal comparison of algorithmic performance, we not only theoretically compare five existing representative recommendation algorithms, but also empirically compare four new algorithms generated based on our findings from the theoretical comparison. Our results show that these algorithms behave similarly in terms of user performance, highlighting the need for more rigorous formal comparisons of recommendation algorithms to further clarify their benefits in various analysis scenarios.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据