DMiner: Dashboard Design Mining and Recommendation

Yanna Lin, Haotian Li, Aoyu Wu, Yong Wang, Huamin Qu

Room: 103

2023-10-25T03:00:00ZGMT-0600Change your timezone on the schedule page
Exemplar figure, described by caption below
The workflow of DMiner. This paper proposes DMiner as a framework for dashboard design mining and automatic recommendation. With the dashboard dataset as the input, DMiner: (A) first surveys a set of features important for dashboard design, and then extracts those features to delineate dashboard designs comprehensively. These are categorized into two types, i.e., single-view features such as data and encoding and pairwise-view features such as coordination and relative position; (B) then mines design rules using decision rule approach, and further filters them; and (C) finally leverages these rules for recommending dashboard arrangement and coordination.
Fast forward
Full Video

Design Mining;Visualization Recommendation;Multiple-view Visualization;Dashboards


Dashboards, which comprise multiple views on a single display, help analyze and communicate multiple perspectives of data simultaneously. However, creating effective and elegant dashboards is challenging since it requires careful and logical arrangement and coordination of multiple visualizations. To solve the problem, we propose a data-driven approach for mining design rules from dashboards and automating dashboard organization. Specifically, we focus on two prominent aspects of the organization: arrangement, which describes the position, size, and layout of each view in the display space; and coordination, which indicates the interaction between pairwise views. We build a new dataset containing 854 dashboards crawled online, and develop feature engineering methods for describing the single views and view-wise relationships in terms of data, encoding, layout, and interactions. Further, we identify design rules among those features and develop a recommender for dashboard design. We demonstrate the usefulness of DMiner through an expert study and a user study. The expert study shows that our extracted design rules are reasonable and conform to the design practice of experts. Moreover, a comparative user study shows that our recommender could help automate dashboard organization and reach human-level performance. In summary, our work offers a promising starting point for design mining visualizations to build recommenders.