Advances in the description and explanation of STAnce in discourse using VIsual and Computational Text Analytics – StaViCTA
This interdisciplinary project across semantics, computational linguistics and information visualization investigates stance in human communication. Stancetaking, which is crucial for the social construction of meaning, involves expressions of attitudes, feelings, perspectives, judgements, doubts, trust or certainty. It is a forceful factor in the communicative dynamics of Web-based social media like websites, blogs, communities, or forums.
StaViCTA focuses on analyzing stance in such real-world streaming language data. Our goal is to identify the resources that language offers, how these resources act together and how they evolve in large amounts of digital text over time. This goal is achieved through the development of innovative, computational and interactive information visualization techniques. We propose a visual text analytics approach for the description, explanation and interpretation of stance in digital text media that includes automatic analyses seamlessly interwoven with interactive visualizations. This combination will make it possible for human beings to make sense of large and dynamic text data and allows for exploration, control and final evaluation of the analysis processes and results. Such an approach for analyzing stance is crucial for many application fields, including intelligence and security analytics, early warning and crisis management systems, financial analytics and business intelligence, and social media monitoring.
Funded by the framework grant "the Digitized Society – Past, Present, and Future" with No. 2012-5659 from the Swedish Research Council (Vetenskapsrådet)