TexTonic: Interactive visualization for exploration and discovery of very large text collections

Abstract

TexTonic is a visual analytic system for interactive exploration of very large unstructured text collections. TexTonic visualizes hierarchical clusters of representative terms, snippets, and documents in a single, multi-scale spatial layout. Exploration is supported by interacting with the visualization and directly manipulating the terms in the visualization using semantic interactions. These semantic interactions steer the underlying analytic model by translating user interactions within the visualization to contextual updates to the supporting data model. The combination of semantic interactions and information visualization at multiple levels of the data hierarchy helps users manage information overload so that they can more effectively explore very large text collections. In this article, we describe TexTonic’s data processing and analytic pipeline, user interface and interaction design principles, and results of a user study conducted mid-development with experienced data analysts. We also discuss the implications TexTonic could have on visual exploration and discovery tasks.

From word clouds to Word Rain: Revisiting the classic word cloud to visualize climate change texts

“…The use of dimensionality reduction to reveal clusters of terms (i.e. topics) in large document collections was also adopted by TexTonic by Paul et al, 31 which combined a spatial metaphor to represent the overall landscape of clusters with a force-directed layout of term labels within the clusters. Compare Clouds by Diakopoulos et al 32 assigned the horizontal positions of individual term labels based on their use in one or both of the specified input corpora in order to reveal, for instance, the patterns of term use on mainstream media versus blogs.…”

An Explanatory Study on User Behavior in Discovering Aggregated Multimedia Web Content

“…The use of SUIs is known to enhance user experience and cognitive engagement [38]. An appealing user interface and interactive visualizations detain the user's interest in the task and keep them captivated to seek the information for a more extended period [41]. As a result, the user can browse more interesting content [36].…”

User Ex Machina : Simulation as a Design Probe in Human-in-the-Loop Text Analytics

“…Many text analytics systems are designed to support human agency, whether this agency takes the form of human-driven "interaction" with [5] or "supervision" of [48] text models. For instance, the iVisClassifier [9] system allows users to supervise the clustering of text corpora, while tools like TextTonic [52] and Dis-Function [5] afford user-driven fine-grained steering of a clustering and layout by, for instance, "pinning" important words, or dragging points the user believes to be misplaced to better locations. However, there are many degrees of freedom in how text models are built, from preparation to analysis to visualization.…”