VisMaker: a Question-Oriented Visualization Recommender System for Data Exploration

TL;DR

VisMaker is a rule-based, question-oriented visualization recommender system designed to assist users in data exploration by simplifying visualization decisions and enhancing understanding through guided recommendations.

Contribution

The paper introduces VisMaker, a novel visualization recommendation tool that organizes suggestions via questions to improve data exploration and decision-making.

Findings

Participants found VisMaker helpful for understanding visualization options.

Compared to Voyager 2, VisMaker provided more accessible recommendations.

User feedback highlighted areas for improving recommendation clarity.

Abstract

The increasingly rapid growth of data production and the consequent need to explore data to obtain answers to the most varied questions have promoted the development of tools to facilitate the manipulation and construction of data visualizations. However, building useful data visualizations is not a trivial task: it may involve a large number of subtle decisions that require experience from their designer. In this paper, we present VisMaker, a visualization recommender tool that uses a set of rules to present visualization recommendations organized and described through questions, in order to facilitate the understanding of the recommendations and assisting the visual exploration process. We carried out two studies comparing our tool with Voyager 2 and analyzed some aspects of the use of tools. We collected feedback from participants to identify the advantages and disadvantages of our recommendation approach. As a result, we gathered comments to help improve the development of tools in this domain.