Mastering Effective Data Visualization with ggplot2 in R: A Hands-on Workshop for Social Work Researchers

Effective data visualization (DV) is essential for communicating research findings and is crucial for Social Work (SW) researchers as they identify trends, patterns, and outliers. The process of DV has always been a vital component of any research project, as it facilitates the extraction of meaningful insights, regardless of the data's complexity (Sarkar 2018) but it is often overlooked in graduate and postgraduate curricula, where advanced statistical analysis takes precedence. DV enables SW researchers to effectively communicate their results within their own discipline, across interdisciplinary boundaries and with a lay audience. In recent years, there has been a remarkable increase in the adoption of visualization as a means to convey messages through data, as exemplified by popular and respected venues such as The New York Times (Pandey et al. 2014) or the utilization of social media platforms like Twitter and Mastodon to increase the access to and visibility of scientific research. Despite being a highly valued skill that all SW researchers should possess, the lack of formal training in graphical design and software programming leads to suboptimal visualizations that impede the dissemination of critical SW findings.

This workshop will teach participants the theory behind and application of good graphical design. Participants will be introduced to the concepts explored in "The Layered Grammar of Graphics" by Hadley Wickham (2010), and they will get hands-on experience building both common and custom visualizations using the free open-source R package, ggplot2. Along the way, participants will learn about the modern application of Gestalt psychology principles, discovered nearly 100 years ago, and how they can be used to develop and evaluate visualizations. By the end of the workshop, attendees will have gained practical skills in the use of both the grammar of graphics and ggplot2, and they will possess a deeper understanding of how a principled approach can enhance the impact of their visualizations, resulting in graphics that are not only visually appealing but also effectively convey their intended message.

This workshop will begin with a lecture comparing examples of poor graphics with good ones while introducing the audience to the grammar of graphics, Gestalt principles and work by Tufte (2001), Cleveland (1985) and Schwabish (2021). Then they will be shown worked examples though live coding. Following this, attendees will access Posit Cloud and will work through interactive, guided tutorials to work on a real ggplot script that results in a publication-ready graphic. All the materials and code will be available free online at the end of the workshop.

In summary, the workshop will utilize a combination of didactic and practical exercises to produce impactful graphics that reduce the cognitive load of the reader while conveying the intended message. Attendees will learn about the various layers of a graph and use the ggplot2 package to create them. By the end of the workshop, participants will have the skills to integrate the data layer, aesthetics layer, and geom layer used by the ggplot2 package to produce effective graphics.