Combining Computational Analyses and Interactive Visualization for Document Exploration and Sensemaking in Jigsaw

Abstract

Investigators across many disciplines and organizations must sift through large collections of text documents to understand and piece together information. Whether they are fighting crime, curing diseases, deciding what car to buy, or researching a new field, inevitably investigators will encounter text documents. Taking a visual analytics approach, we integrate multiple text analysis algorithms with a suite of interactive visualizations to provide a flexible and powerful environment that allows analysts to explore collections of documents while sensemaking. Our particular focus is on the process of integrating automated analyses with interactive visualizations in a smooth and fluid manner. We illustrate this integration through two example scenarios: an academic researcher examining InfoVis and VAST conference papers and a consumer exploring car reviews while pondering a purchase decision. Finally, we provide lessons learned toward the design and implementation of visual analytics systems for document exploration and understanding.

Speculative Practices: Utilizing InfoVis to Explore Untapped Literary Collections

“…This strategy has been extensively discussed in the visualization community to facilitate investigative analysis [45,53], the exploration of news articles [11], book collections [46], and artworks [21]. Studies have shown that the strategy of coordinated views is useful for the analysis of large and complex document collections, both in professional [5,18] and casual contexts [11,21]. Thudt et al highlight this strategy as particularly effective for supporting open-ended exploration and serendipitous discoveries [46].…”

GraphDocExplore: A Framework for the Experimental Comparison of Graph-based Document Exploration Techniques

“…In addition to specific graphs, more complex applications, such as new/s/leak (Yimam et al, 2016), Jigsaw (Görg et al, 2013) or Overview 2 , have been developed to support document exploration by integrating many different techniques, including graphs, in a single application. In contrast to our work, their focus is on productive use, while we are mainly interested in the experimental evaluation, requiring us to study the use of specific graphs in isolation.…”

Visual Analytics Support for Intelligence Analysis

“…An extensive discussion of academic research projects employing visual analytics for understanding text and document collections can be found in [2]. The scenario exploring the 9/11 Commission Report and the images used in this article were produced using the Jigsaw visual analytics system.…”

“…Early versions of Jigsaw emphasized a suite of interactive visualizations portraying the documents' contents and connections between entities in the documents [10]. More recently, we have integrated computational text analysis capabilities [2]. Beyond intelligence analysis, Jigsaw has been used to explore consumer review, academic research, fraud, investigative reporting, law enforcement, business intelligence, and email document collections.…”

“…Two fundamental types of investigative scenarios exist within the intelligence domain: (1) targeted analysis scenarios, in which analysts are tasked with examining specific people, organizations, or incidents, as well as locations and dates, in order to either investigate past events or uncover an imminent threat, and (2) open ended, ⇤ e-mail: Carsten.Goerg@ucdenver.edu † e-mail: ykang@google.com ‡ e-mail: zcliu@cs.stanford.edu § e-mail: stasko@cc.gatech.edu strategic analysis scenarios, in which analysts are tasked with learning as much as possible about a person, organization, country, or situation in order to gain a deeper understanding, conduct an accurate assessment, and possibly make a prediction on the likely chain of events that will occur at a later point in time. Examining and understanding large collections of textual documents plays an important role in both types of these scenarios.…”