ViTA: Visualization for Text Alignment

In this lecture, I will present a web-based visual analytics approach for detecting similarity between texts. ViTA: Visualization for Text Alignment is the result of our “Commonplace Cultures: Mining Shared Passages in the 18th Century using Sequence Alignment and Visual Analytics” project under the Digging into Data Challenge Program (III) and it is a collaboration between the University of Oxford, the University of Chicago, and the Australian National University. The team comprises of computer scientists and domain experts in the fields of literary studies, intellectual history, and digital humanities. ViTA is a web-based visual analytics approach that allows domain experts to construct and modify a text alignment pipeline by visualizing the tools and connections for a specific method in conjunction with testing inputs and outputs. The construction of the text alignment is similar to that of an image processing pipeline. As the approach was embedded directly in the context of 18th century print culture, this approach was developed in an interdisciplinary manner, and was evaluated in intensive meetings with the domain experts at the design stage as well as after prototyping.