1 Visual Analytics 2 CS 7450 - Information Visualization November 20, 2013 John Stasko Topic Notes Agenda • Last time  Overview of what the term means and how it relates to information visualization  Some example VA research projects • Today  Specific example, Jigsaw, helping investigative analysis  Related systems Fall 2013 CS 7450 22 VA Definition • Visual analytics combines automated analysis techniques with interactive visualizations for an effective understanding, reasoning and decision making on the basis of very large and complex data sets Keim et al, chapter in Information Visualization: Human-Centered Issues and Perspectives, 2008 Fall 2013 CS 7450 Review 3 Application Area • Investigative & Intelligence Analysis  Gather information from various sources then analyze and reason about what you find and know  Analyze situations, understand the particulars, anticipate what may happen Fall 2013 CS 7450 43 5 5 Definitions • Thinking1 - or reasoning - involves objectively connecting present beliefs with evidence in order to believe something else • Critical Thinking1 is a deliberate meta-cognitive(thinking about thinking) thinking act whereby a person reflects on the quality of the reasoning process simultaneously while reasoning to a conclusion. • Intelligence1 is a specialized form of knowledge, an activity, and an organization. As knowledge, intelligence informs leaders, uniquely aiding their judgment and decision-making. … 1. Critical Thinking and Intelligence Analysis: David Moore CS 7450 5 6 Critical Thinking* “…the quality of our life and that of what we produce, make, or build depends precisely on the quality of our thoughts.” * Foundations of Critical Thinking www.criticalthinking.org Elements of thought: Points of View Purpose of the Thinking Question at Issue Information Interpretation And Inference Concepts Assumptions Implications & Consequences CS 7450 64 7 Example: Heuer’s Central Ideas • “Tools and techniques that gear the analyst’s mind to apply higher levels of critical thinking can substantially improve analysis… structuring information, challenging assumptions, and exploring alternative interpretations.” CS 7450 7 Intelligence Process Pirolli & Card Intl Conf Intelligence Analysis ‘05 CS 7450 Fall 2013 85 Intelligence Process Fall 2013 CS 7450 9 Wheaton In preparation Pain Points • Cost structure of scanning and selecting items for further attention • Analysts’ span of attention for evidence and hypotheses Fall 2013 CS 7450 106 Jigsaw Visualization for Investigative Analysis across Document Collections Law enforcement & intelligence community Fraud (finance, accounting, banking) Academic research Journalism & reporting Consumer research “Putting the pieces together”“Putting the pieces together” Fall 2013 CS 7450 11 Stasko, Görg, Liu Information Visualization ‘08 Görg et al TVCG ‘13 Problem Addressed Help “investigators” explore, analyze and understand large document collections Articles & Articles & reportsreports BlogsBlogs SpreadsheetsSpreadsheets XML documentsXML documents Fall 2013 CS 7450 127 The Jigsaw Team Carsten Görg Zhicheng Liu Youn-ah Kang Jaeyeon Kihm Jaegul Choo Chad Stolper Anand Sainath and many others Fall 2013 CS 7450 13 Our Focus • Entities within the documents  Person, place, organization, phone number, date, license plate, etc. • Thesis: A story/narrative/plot/threat within the documents will involve a set of entities in coordination Fall 2013 CS 7450 148 Doc 1 Doc 2 Doc 3 John Smith June 1, 2009 Atlanta PETA Boston Mary Wilson Bill Jones Fall 2013 CS 7450 15 Entity Identification • Must identify and extract entities from plain text documents  Crucial for our work • Not our main research focus – We use tools from others Fall 2013 CS 7450 169 Sample Document Fall 2013 CS 7450 17 Entities Identified Fall 2013 CS 7450 1810 Sample Document 2 Title: Proving Columbus was Wrong Abstract: In this work, we show the world is really flat. To do this, we build a bunch of ships. Then we… PI: Amerigo Vespucci Co-PI: Vasco de Gama, Ponce de Leon Organization: Northwest Central Univ. Amount: 123,456 Program Mgr: Ephraim Glinert Division: IIS ProgramElementCode: 2860 Fall 2013 CS 7450 19 Entities Already Identified Title: Proving Columbus was Wrong Abstract: In this work, we show the world is really flat. To do this, we build a bunch of ships. Then we… PI: Amerigo Vespucci Co-PI: Vasco de Gama, Ponce de Leon Organization: Northwest Central Univ. Amount: 123,456 Program Mgr: Ephraim Glinert Division: IIS ProgramElementCode: 2860 Fall 2013 CS 7450 2011 Connections • Entities relate/connect to each other to make a larger “story” • Connection definition:  Two entities are connected if they appear in a document together  The more documents they appear in together, the stronger the connection Fall 2013 CS 7450 21 Jigsaw • Computational analysis of document text  Entity identification, document similarity, clustering, summarization, sentiment • Multiple visualizations (views) of documents, analysis results, entities and their connections • Views are highly interactive and coordinated “Putting the pieces together” Fall 2013 CS 7450 2212 System Views Fall 2013 CS 7450 23 Pixels Help 24 Fall 2013 CS 745013 Fall 2013 CS 7450 25 Fall 2013 CS 7450 2614 Fall 2013 CS 7450 27 Console Fall 2013 CS 7450 28 Entity types15 Document View Important words in loaded docs Automatic summary Entities identified Fall 2013 CS 7450 29 List View Lists of entities by type Connections highlighted Fall 2013 CS 7450 3016 Graph View Document Entities Fall 2013 CS 7450 31 WordTree View Context of a word in the collection Fall 2013 CS 7450 3217 Document Cluster View Clustered by document text or by entities Summarized by three words Fall 2013 CS 7450 33 Document Grid View Sentiment analysis shown here User controls order and color Fall 2013 CS 7450 3418 Calendar View Showing connections between entities and dates Fall 2013 CS 7450 35 Circular Graph View Connections between entities Fall 2013 CS 7450 3619 Scatterplot View Documents containing pairs of entities Fall 2013 CS 7450 37 Demo 1 • Car reviews  Text: Consumer’s comments  Entities: Various ratings (1-10), car features, other makes & models Fall 2013 CS 7450 3820 Demo 2 • InfoVis & VAST papers  Text: paper