Visual Text Analytics

Motivation

Visualizing textual information is a particularly challenging area of information visualization and visual analytics research. The types of data processing and analytic algorithms differ greatly from tabular or geospatial data, and the visualization techniques have additional constraints to consider, including the provision of context for text fragments of similar or different size and structure, depicting embeddings and high dimensional representations, and ensuring legibility of text incorporated into visualizations. The wide variation in data is accompanied by the difficulties in inferring the semantic meaning of ambiguous terms, or determining the referencing between subsequent statements.

This Dagstuhl Seminar aims to bring together researchers from the visualization, natural language processing (NLP), and machine learning communities, with domain experts from several text-related research areas, to identify the most pressing and promising open problems for collaborative research. A truly interdisciplinary approach may offer new opportunities to capitalize on existing knowledge and recent developments across all involved disciplines. We will focus on a comprehensive discussion of visual text analytics, with a goal to provide an application-oriented research agenda. The main themes for the seminar cover theory, methodology, and application:

1. Data Sources and Diversity What is the current landscape of the application fields and data domains? What are the data gaps? Can existing approaches be generalized?
2. Model Explainability and Interpretability Can we provide more sophisticated visualizations to study how language models learn or what information they represent?
3. Evaluation and Experimental Designs Which experimental methods best support the evaluation of techniques and processes for visualizing text information?
4. Interaction Design What design opportunities are unique to, or more pressing, for text data? How can interaction principles be applied to any underlying NLP as well?
5. Toolkits and Standards What success stories regarding existing text visualization approaches and systems can we learn from? What is needed?
6. TextVis Literacy Visual text analytics can be applied across a wide variety of domains. How do we make techniques easy to learn and to interpret correctly?

The seminar will coalesce the community of experts from different disciplines around a research roadmap for the next 5–10 years. We aim to generate a series of research questions as a call to action by the wider community. The research discussed at the seminar will provide a deeper and more holistic understanding of challenges and opportunities in visual text analytics. The unique and contained setting of Schloss Dagstuhl will facilitate new collaborations and allow us to lay the groundwork for productive future collaborations.