VizML

Hu, Kevin; Bakker, Michiel A.; Li, Stephen; Kraska, Tim; Hidalgo, César A.

doi:10.1145/3290605.3300358

Cited by 143 publications

(49 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Systems that propose visualizations could suggest better ways to present user-selected features [20], [21], [22], visually support users in feature selection [23], or suggest interesting features to visualize [24], [25], [26], [27]. For example, Stolper et al [28] offers progressive visual analysis, a paradigm that allows users to explore semantically relevant partial findings in integrated, interactive visualizations as analyses are performed.…”

Section: B Guidance For Visual Data Analysismentioning

confidence: 99%

VALS: Supporting Visual Data Analysis in Longitudinal Clinical Studies

Betancur

Charpak²,

Montealegre‐Pomar³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Visual data analysis helps to understand different types of phenomena by allowing experts to explore for relationships, patterns, outliers, unexpected changes, and more. Experts need tools that help them find useful and actionable information in the data so they can test their hypotheses and come up with new ones. This need becomes more evident in cases of longitudinal studies, where there are usually a large number of variables and the process being analyzed can be complex as well. We present VALS (Visual Analytics in Longitudinal Studies), a framework for visually exploring longitudinal clinical data. VALS includes a data model, a task categorization model, and an approach to guidance through feature engineering techniques and interactive visualizations, all to help analysts perform their analysis tasks. VALS has been designed in collaboration with healthcare experts with experience in longitudinal studies. We have also developed a tool prototype for a case study using real-world datasets. The evidence collected in the case study shows how useful a VALS-based visual analytics tool can be.

show abstract

Section: B Guidance For Visual Data Analysismentioning

confidence: 99%

VALS: Supporting Visual Data Analysis in Longitudinal Clinical Studies

Betancur

Charpak²,

Montealegre‐Pomar³

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The artifact would occupy that preparation phase, but its properties would reflect its machine progenitor. Conversely, a dashboard of the model's results is an artifact that exists in a communication process and likewise can be meticulously curated by a human or be automatically generated [41].…”

Section: Automl Artifactsmentioning

confidence: 99%

Tracing and Visualizing Human-ML/AI Collaborative Processes through Artifacts of Data Work

Rogers

Crisan

2023

Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

show abstract

“…Building on seminal automatic visualization work by Jock Mackinlay [48], Tableau's Show Me [49] feature recommends charts based on data types as well as best practices. Since then, various types of recommendation tools have been developed, such as those based on data properties [41,83], perceptual principles [83], expert feedback [47], large-scale datasetvisualization pairs [34], and design knowledge [54].…”

Section: Facilitating the Chart Design Processmentioning

confidence: 99%