Multi-model semantic interaction for text analytics

Semantic interaction offers an intuitive communication mechanism between human users and complex statistical models. By shielding the users from manipulating model parameters, they focus instead on directly manipulating the spatialization, thus remaining in their cognitive zone. However, this technique is not inherently scalable past hundreds of text documents. To remedy this, we present the concept of multi-model semantic interaction, where semantic interactions can be used to steer multiple models at multiple levels of data scale, enabling users to tackle larger data problems. We also present an updated visualization pipeline model for generalized multi-model semantic interaction. To demonstrate multi-model semantic interaction, we introduce StarSPIRE, a visual text analytics prototype that transforms user interactions on documents into both small-scale display layout updates as well as large-scale relevancy-based document selection.

[1]  James J. Thomas,et al.  Visualizing the non-visual: spatial analysis and interaction with information from text documents , 1995, Proceedings of Visualization 1995 Conference.

[2]  Robert R. Korfhage,et al.  Visualization of a Document Collection: The VIBE System , 1993, Inf. Process. Manag..

[3]  Edward M. Reingold,et al.  Graph drawing by force‐directed placement , 1991, Softw. Pract. Exp..

[4]  Jean Scholtz,et al.  VAST 2007 Contest - Blue Iguanodon , 2007, 2007 IEEE Symposium on Visual Analytics Science and Technology.

[5]  Kim Nam Chow.  Connect the dots , 2003 .

[6]  Chris North,et al.  Semantics of Directly Manipulating Spatializations , 2013, IEEE Transactions on Visualization and Computer Graphics.

[7]  Alex Endert,et al.  Semantic Interaction for Visual Analytics: Inferring Analytical Reasoning for Model Steering , 2016, Semantic Interaction for Visual Analytics.

[8]  Ian T. Jolliffe,et al.  Principal Component Analysis , 2002, International Encyclopedia of Statistical Science.

[9]  Michael C. Hout,et al.  Multidimensional Scaling , 2003, Encyclopedic Dictionary of Archaeology.

[10]  M. E. Maron,et al.  On Relevance, Probabilistic Indexing and Information Retrieval , 1960, JACM.

[11]  Marti A. Hearst.  TileBars: visualization of term distribution information in full text information access , 1995, CHI '95.

[12]  William Ribarsky,et al.  Building and Applying a Human Cognition Model for Visual Analytics , 2009, Inf. Vis..

[13]  William Ribarsky,et al.  iPCA: An Interactive System for PCA‐based Visual Analytics , 2009, Comput. Graph. Forum.

[14]  P. Pirolli,et al.  The Sensemaking Process and Leverage Points for Analyst Technology as Identified Through Cognitive Task Analysis , 2007 .

[15]  Gary Marchionini,et al.  A self-organizing semantic map for information retrieval , 1991, SIGIR '91.

[16]  Chris North,et al.  How analysts cognitively “connect the dots” , 2013, 2013 IEEE International Conference on Intelligence and Security Informatics.

[17]  Jaegul Choo,et al.  Customizing Computational Methods for Visual Analytics with Big Data , 2013, IEEE Computer Graphics and Applications.

[18]  Carla E. Brodley,et al.  Dis-function: Learning distance functions interactively , 2012, 2012 IEEE Conference on Visual Analytics Science and Technology (VAST).

[19]  Stuart K. Card,et al.  Visualizing retrieved information: a survey , 1996, IEEE Computer Graphics and Applications.

[20]  Alexander W. Skaburskis,et al.  The Sandbox for analysis: concepts and methods , 2006, CHI.

[21]  Ramana Rao,et al.  A focus+context technique based on hyperbolic geometry for visualizing large hierarchies , 1995, CHI '95.

[22]  Chris North,et al.  Observation-level interaction with statistical models for visual analytics , 2011, 2011 IEEE Conference on Visual Analytics Science and Technology (VAST).

[23]  John T. Stasko,et al.  Jigsaw: Supporting Investigative Analysis through Interactive Visualization , 2007, 2007 IEEE Symposium on Visual Analytics Science and Technology.

[24]  W. Torgerson.  Multidimensional scaling: I. Theory and method , 1952 .

[25]  Chris North,et al.  The semantics of clustering: analysis of user-generated spatializations of text documents , 2012, AVI.

[26]  Christopher Andrews,et al.  Helping Intelligence Analysts Make Connections , 2011, Scalable Integration of Analytics and Visualization.

[27]  T. Landauer,et al.  Indexing by Latent Semantic Analysis , 1990 .

[28]  Chris North,et al.  Semantic interaction for visual text analytics , 2012, CHI.

[29]  Frank M. Shipman,et al.  Formality Considered Harmful: Experiences, Emerging Themes, and Directions on the Use of Formal Representations in Interactive Systems , 1999, Computer Supported Cooperative Work (CSCW).

[30]  Scott P. Robertson,et al.  Proceedings of the SIGCHI Conference on Human Factors in Computing Systems , 1991 .

[31]  Christopher Andrews,et al.  Co-located Collaborative Sensemaking on a Large High-Resolution Display with Multiple Input Devices , 2011, INTERACT.

[32]  John T. Stasko,et al.  Dust & Magnet: Multivariate Information Visualization Using a Magnet Metaphor , 2005, Inf. Vis..

[33]  Analyst's Workspace: An embodied sensemaking environment for large, high-resolution displays , 2012, 2012 IEEE Conference on Visual Analytics Science and Technology (VAST).

[34]  Christopher Andrews,et al.  Space to think: large high-resolution displays for sensemaking , 2010, CHI.

[35]  Chris North,et al.  Beyond Control Panels: Direct Manipulation for Visual Analytics , 2013, IEEE Computer Graphics and Applications.

[36]  Michael Benedikt,et al.  Cyberspace: some proposals , 1991 .

[37]  Richard K. Belew,et al.  Adaptive information retrieval: using a connectionist representation to retrieve and learn about documents , 1989, SIGIR '89.