Castor, Pollux, and Gemini
Castor, Pollux, and Gemini are three different implementations of a computational pipeline that projects high-dimensional data into an interactive visualization, combining both dimension reduction and clustering algorithms in the projection. Semantic interactions are implemented within the interface, allowing an analyst to provide implicit task feedback to an underlying machine learning component. With this feedback, an analyst can interact directly with the data to express their interests, incrementally training those underlying models and causing future updates to the visualization to better reflect the dimensions of interest to the analyst. The overarching goal of this research is to explore both the design and interaction space at the intersection of dimension reduction algorithms, clustering algorithms, and semantic interaction.
Related publications:
- John Wenskovitch, Michelle Dowling, and Chris North. “Towards Addressing Ambiguous Interactions and Inferring User Intent with Dimension Reduction and Clustering Combinations in Visual Analytics,” ACM Transactions on Interactive Intelligent Systems (TiiS), 14(1) (Mar. 2024). DOI: 10.1145/3588565.
- John Wenskovitch and Chris North. “Pollux: Interactive Cluster-First Projections of High-Dimensional Data,” in 2019 Symposium on Visualization in Data Science. VDS’19. Vancouver, BC, Canada, Oct. 2019, pp. 38-47. DOI: 10.1109/VDS48975.2019.8973381.
- John Wenskovitch, Ian Crandell, Naren Ramakrishnan, Leanna House, Scotland Leman, and Chris North. “Towards a Systematic Combination of Dimension Reduction and Clustering in Visual Analytics,” IEEE Transactions on Visualization and Computer Graphics, 24(1) (Jan. 2018), pp. 131–141. DOI: 10.1109/TVCG.2017.2745258. Presented at IEEE VIS (VAST) 2017.
- John Wenskovitch and Chris North. “Observation-Level Interaction with Clustering and Dimension Reduction Algorithms,” in Proceedings of the 2nd Workshop on Human-In-the-Loop Data Analytics. HILDA’17. Chicago, IL, USA: ACM, 2017, 14:1–14:6. DOI: 10.1145/3077257.3077259.
StarSPIRE and Semantic Interaction Foraging
StarSPIRE is a visual analytics tool designed to explore collections of documents, leveraging users’ semantic interactions to steer (1) a synthesis model that aids in document layout and (2) a foraging model to automatically retrieve new relevant information. In contrast to traditional keyword search foraging, “semantic interaction foraging” occurs as a result of the user’s synthesis actions. To quantify the value of semantic interaction foraging, we used StarSPIRE to evaluate its utility for an intelligence analysis sensemaking task. We found that semantic interaction foraging accounted for 26% of useful documents found, and it also resulted in increased synthesis interactions and improved sensemaking task performance by users in comparison to only using keyword search. Completing text analysis tasks is a continuous sensemaking loop of foraging for information and incrementally synthesizing it into hypotheses.
Related publication:
- John Wenskovitch, Lauren Bradel, Michelle Dowling, Leanna House, and Chris North. “The Effect of Semantic Interaction on Foraging in Text Analysis,” in 2018 IEEE Conference on Visual Analytics Science and Technology (VAST). Oct. 2018, pp. 13–24. DOI: 10.1109/VAST.2018.8802424.
Interaction Provenance Research
There is fast-growing literature on provenance research, covering aspects such as its theoretical framework, use cases, and techniques for capturing, visualizing, and analyzing provenance data. As a result, there is an increasing need to identify and taxonomize the existing scholarship. Such an organization of the research landscape will provide a complete picture of the current state of inquiry and identify knowledge gaps or possible avenues for further investigation. My research in this area includes a state-of-the-art (STAR) report, producing a comprehensive survey of work in the data visualization and visual analytics field that focus on the analysis of user interaction and provenance data. The survey and papers discussed can be explored online interactively. My work also proposes a task abstraction framework that consists of a three stage approach, composed of (1) initializing a provenance task hierarchy, (2) parsing the provenance hierarchy by using an abstraction mapping mechanism, and (3) leveraging the task hierarchy in an analytical tool.
Related publications:
- Kai Xu, Alvitta Ottley, Conny Walchshofer, Marc Streit, Remco Chang, and John Wenskovitch. “Survey on the Analysis of User Interactions and Visualization Provenance,” The Eurographics Association and John Wiley & Sons Ltd., 2020. DOI: 10.1111/cgf.14035.
- Christian Bors, John Wenskovitch, Michelle Dowling, Simon Attfield, Leilani Battle, Alex Endert, Olga Kulyk, and Robert S. Laramee. “A Provenance Task Abstraction Framework,” Computer Graphics & Applications (2019), pp. 1–15. DOI: 10.1109/MCG.2019.2945720.
SIRIUS, Cosmos, and Andromeda
In addition to Castor, Pollux, and Gemini above, my research has also supported similar tools that vary the user interface and types of data that are supported by the systems. SIRIUS presents a dual-view display, permitting semantic interactions to be applied to both the data objects and their attributes. Cosmos introduces an Elasticsearch component to support larger data sets, modeling the synthesis loop as an interactive spatial projection and the foraging loop as an interactive relevance ranking combined with topic modeling.
Related publications:
- John Wenskovitch and Chris North. “An Examination of Grouping and Spatial Organization Tasks for High-Dimensional Data Exploration,” IEEE Transactions on Visualization and Computer Graphics, 27(2) (Feb. 2021), pp. 1742-1752. DOI: 10.1109/TVCG.2020.3028890. Presented at IEEE VIS 2020.
- Ming Wang, John Wenskovitch, Leanna House, Nicholas Polys, and Chris North. “Bridging Cognitive Gaps Between User and Model in Interactive Dimension Reduction,” Visual Informatics (2021). DOI: 10.1016/j.visinf.2021.03.002.
- Michelle Dowling, Nathan Wycoff, Brian Mayer, John Wenskovitch, Scotland Leman, Leanna House, Nicholas Polys, Chris North, and Peter Hauck. “Interactive Visual Analytics for Sensemaking with Big Text,” Big Data Research, 16 (July 2019), pp. 49–58. DOI: 10.1016/j.bdr.2019.04.003.
- Michelle Dowling, John Wenskovitch, J.T. Fry, Scotland Leman, Leanna House, and Chris North. “SIRIUS: Dual, Symmetric, Interactive Dimension Reductions,” IEEE Transactions on Visualization and Computer Graphics, 25(1) (Jan. 2019), pp. 172–182. DOI: 10.1109/TVCG.2018.2865047. Presented at IEEE VIS (VAST) 2018.
- Jessica Zeitz Self, Michelle Dowling, John Wenskovitch, Ian Crandell, Ming Wang, Leanna House, Scotland Leman, and Chris North. “Observation-Level and Parametric Interaction for High-Dimensional Data Analysis,” ACM Transactions on Interactive Intelligent Systems (TiiS), 8(2) (June 2018), 15:1–15:36. DOI: 10.1145/3158230.
- Xin Chen, Jessica Zeitz Self, Leanna House, John Wenskovitch, Maoyuan Sun, Nathan Wycoff, Jane Robertson Evia, Scotland Leman, and Chris North. “Be the Data: Embodied Visual Analytics,” IEEE Transactions on Learning Technologies, 11(1) (Jan. 2018), pp. 81–95. DOI: 10.1109/TLT.2017.2757481.
