Semantic Wordification of Document Collections

Abstract

Word clouds have become one of the most widely accepted visual resources for document analysis and visualization, motivating the development of several methods for building layouts of keywords extracted from textual data. Existing methods are effective to demonstrate content, but are not capable of preserving semantic relationships among keywords while still linking the word cloud to the underlying document groups that generated them. Such representation is highly desirable for exploratory analysis of document collections. In this paper we present a novel approach to build document clouds, named ProjCloud that aim at solving both semantical layouts and linking with document sets. ProjCloud generates a semantically consistent layout from a set of documents. Through a multidimensional projection, it is possible to visualize the neighborhood relationship between highly related documents and their corresponding word clouds simultaneously. Additionally, we propose a new algorithm for building word clouds inside polygons, which employs spectral sorting to maintain the semantic relationship among words. The effectiveness and flexibility of our methodology is confirmed when comparisons are made to existing methods. The technique automatically constructs projection based layouts the user may choose to examine in the form of the point clouds or corresponding word clouds, allowing a high degree of control over the exploratory process.

OpenEssayist

“…These options aim to encourage students to consider whether their essay contains the key concepts and development of argument that they intended. The third main component, 'graphics', includes two different visual representations of key words: as a word cloud, a very common technique for visual analysis of documents which gives prominence to frequent words [13]; and as a dispersion plot, showing the distribution of key words through the essay. The graphics landing screen offers two ways to view the word count in terms of how the word count is divided across the essay sections and how the word count aligns with the word limit.…”

Visual Exploration of Relationships between Document Clusters

“…Tag clouds [Kaser and Lemire, 2007] are one approach to visualize the frequency of words in a document or the keywords of a document collection, and there are several very popular tools which extend the original work, such as Wordle [Viegas et al, 2009], ManiWorlde [Koh et al, 2010], or ProjCloud [Paulovich et al, 2012]. Our prototype uses a simple version of tag clouds to show common keywords of documents that were clustered together.…”

Visualização da evolução temporal de coleções de artigos científicos

“…A técnica ProjCloud (Paulovich et al, 2012) cria um mapa de documentos que combina técnicas de projeção multidimensional com tag clouds. Primeiramente, a coleção é projetada utilizando a LSP (poderia ser utilizada qualquer outra técnica de projeção).…”