Professor Min Chen delivers capstone talk at EuroVA 2016

Professor Min Chen delivers capstone talk at EuroVA 2016

Professor of Scientific Visualisation Min Chen delivered the capstone talk at EuroVA 2016, the seventh international EuroVis workshop on Visual Analytics taking place on 6-7 June in Groningen, the Netherlands.

His talk, entitled 'Building a Theoretical Foundation for Visual Analytics', reported on discussions held during the recent Alan Turing Institute Symposium on Theoretical Foundation of Visual Analytics, held at the Oxford e-Research Centre.

Professor Chen also summarised the State of the Art in four aspects of such a foundation, namely taxonomies, principles and guidelines, conceptual frameworks and models, and quantitative laws. He described an information-theoretic metric for measuring the cost-benefit of machine- and human-centric processes in data intelligence, and demonstrated that one can mathematically reason the merits of visualization and interaction in most data intelligence applications.

Visual Analytics deals with problems that cannot (yet) be solved algorithmically and therefore essentially require human thinking supported by the power of computers. It is an interdisciplinary science integrating techniques from visualization and computer graphics, statistics and mathematics, data management and knowledge representation, data analysis and machine learning, cognitive and perceptual sciences, and more.

Professor Chen co-authored on a paper presented at the related EuroVis conference, the 18th annual visualization gathering organized by the Eurographics Working Group on Data Visualization.

The objective of EuroVis is to foster greater exchange between visualization researchers and practitioners, and to draw more researchers and industry partners in Europe to enter this rapidly growing area of research. EuroVis has an expanded scope to include all areas of visualization, and a steadily more wide-spread visibility that achieves a more wide-spread impact.

Professor Chen's paper, How Ordered Is It? On the Perceptual Orderability of Visual Channels, presented two crowdsourcing empirical studies that focus on the perceptual evaluation of orderability for visual channels, namely Bertin's retinal variables.

Colleague Dr Alfie Abdul-Rahman also presented a paper on 9 June at EuroVis entitled Constructive Visual Analytics for Text Similarity Detectionwhich was published in Computer Graphics Forum in February this year. Detecting similarity between texts is a frequently encountered text mining task. Because the measurement of similarity is typically composed of a number of metrics, and some measures are sensitive to subjective interpretation, a generic detector obtained using machine learning often has difficulties balancing the roles of different metrics according to the semantic context exhibited in a specific collection of texts.

The paper describes how, in order to facilitate human interaction in a visual analytics process for text similarity detection, the researchers first map the problem of pairwise sequence comparison to that of image processing, allowing patterns of similarity to be visualized as a 2D pixelmap. They then devise a visual interface to enable users to construct and experiment with different detectors using primitive metrics, in a way similar to constructing an image processing pipeline.

This new approach was deployed in the identification of commonplaces in 18th-century literary and print culture. Domain experts were then able to make use of the prototype system to derive new scholarly discoveries and generate new hypotheses.