ARTigo: Lessons From Social Image Tagging in an Art-Historical Game With a Purpose

Abstract

Since 2010, ARTigo has been leveraging games with a purpose (GWAPs) to engage citizen scientists in the tagging of artworks. In these games, two players collaboratively annotate images under time constraints. This paper introduces ARTigo as an easily customizable framework for image labeling tailored to elicit specific domain knowledge. It also outlines a two-pronged evaluation strategy to assess the impact of ARTigo’s front-end design on visual aesthetics, usability, and cognitive workload, as well as on users' tagging behavior. Comparisons between ARTigo version $\boldsymbol {1}$, developed from 2010 to 2013, and version $\boldsymbol {2}$, developed in 2022, indicate significant improvements: the System Usability Scale rating improved from grade B to A-, and the Short Visual Aesthetics of Websites Inventory rating from 4.42 to 5.34 points ($\boldsymbol {p < 0.05}$). Moreover, the graphical user interface in version $\boldsymbol {2}$ promotes more frequent and complex tagging, thus collecting a similar amount of tags with higher entropy in fewer rounds—which is especially beneficial for GWAP with smaller, active communities.