Browsing Documents on a Dense Embedding that Captures Theme Evolution

We describe a new interaction strategy for browsing documents consisting of text and images. The browser represents a collection of documents as a grid of key words with varying font sizes that indicate the words’ weights. The grid is computed using the counting grid model [7], so that each document approximately matches in its word usage the word weight distribution in some window (6 × 6 in our experiments) in the grid. In comparison to other document embedding approaches, this strategy leads to denser packing of documents and higher relatedness of nearby documents: The two documents that map to overlapping windows literally share the words found in the overlap. This leads to smooth thematic shifts that can provide connections among distant topics on the grid. The images are embedded into the appropriate locations in the grid, so that a mouse over any location can invoke a pop-up of the images mapped nearby. Once the user locks on an interesting spot in the grid, the summaries of the actual documents that mapped in the vicinity are listed for selection. In this document browser the arrangement of related words and themes on the grid naturally guides the user’s attention to topics of interest. For an illustration we describe and demonstrate (in video submission) a browser of four months of CNN news. INTRODUCTION Summarizing, visualizing and browsing text corpora are important problems in computer-human interaction. As the data becomes more massive, ambiguous, or conflicting, it may become hard for people to glean insights from it. To help the users, researchers have developed several visual analytics tools facilitating the analysis of such corpora. These tools are used to interactively make sense of complex datasets, a process referred to as sensemaking [10]. We describe a new approach to browsing documents consisting of text and images, e.g. news stories on the web, social media, special interest web sites, etc. The browsing through documents is based on the exploration of the hidden variable Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. CHI’13, April 27–May 2, 2013, Paris, France. Copyright 2013 ACM 978-1-XXXX-XXXX-X/XX/XX...$10.00. of the on the counting grid (CG) generative model [7], which has recently been used for a variety of tasks related to regression and classification. The counting grid model represents the space of possible documents as a grid of word counts. Each individual document is mapped to a window into this grid so that the tally of these counts approximately matches the word counts in the document. The grid can vary in size, and so can the window. As the documents are allowed to be mapped with overlap, in order to maximize the likelihood of the data, the learning algorithm has to map similar documents to nearby locations in the grid, so that the words that the two documents share appear in the grid positions in the overlap of the corresponding windows. This leads to a compact representation where the theme of the documents smoothly varies across the grid, achieving a higher density of packing than previous embedding approaches (e.g. Egypt unrest news are placed close to other stories about Arab Spring, with Libya taking another distinct location in that area of the CG; nearby are stories about oil prices, and near these are more stories about the markets and economy, near which are stories referring to Fed’s Bernanke, near which are stories about congress and the President, which, in a counting grid defined on a torus may loop back to Libya through military themes.) To provide natural means of summarization and browsing of the documents, we render a CG representation based only on the most frequent words in each position. We further embed the images from each document into the appropriate locations in the counting grid, so that they can pop up when the user focuses on a particular area of the grid (e.g. by mouse over). This provides the user with both a global and local perspective on the underlying set of documents and their relationships, without observing directly the underlying documents, but rather the CG model’s representation of the document space. Once the user locks on an interesting spot in the grid, the summaries of the actual documents that mapped in the vicinity are listed for selection. This idea leads to an intuitive document browser that is especially well suited to touch devices, where moving a cursor is the most natural interaction modality, while typing is particularly difficult. Additionally, the interface assists the user in discovering documents of interest without having to define a particular target and associated keywords first: The arrangement of related words and themes on the grid naturally guides the user’s attention to topics of interest. For an illustration we describe and demonstrate (video submission) a browser of four months of CNN news from winter and spring 2011, a period particularly rich in news-worthy events. COUNTING GRIDS (CGS) music alcohol religi afghan failur con ict attack oldest brought robertson attack particip muslim minist group spirit religi mean pope mean radic rock threw holm islamist scene angri egypt mubarak hosni in uenc spirit blame speech radic youth corrupt ralli toppl inspir protest peac peac protest gather homeland reason oil syria undermin islam zine abidin tunisia protest sanaa ouster demonstr chant prodemocraci crazi recent rid repeat revolut cabl tunisia upris tunisian ben tuni ali unrest demonstr protest realiz side lose cabl ra local ee capit upris capit regim clash protest africa opposit hear closer adopt ght gun r unanim african ambassador asset libya tripoli crackdown daraa opposit libya refer ban loss sanction eastern diplomat libya gadha libyan libya gadha moammar gadha libyan libya ban altern kimoon council secretarygener resolut libyan resolut rebel libyan libya moammar libyan gadha misrata cuba justic digniti council necessari aircraft gbagbo ouattara ivori nato gbagbo rebel coalit no i ghter court guantanamo trial necessari o er unit militari civilian nato nato militari civilian bomb no i strike i-1 i i+1 19 Jan 2011 : Protesters march in Tunis amid Arab League fears 27 Jan 2011 : Social media's role in North Africa's unrest 11 Apr 2011 : None of us was Gadha 's lover, one of his nurses says 28 Feb 2011 : N. Africa, Mideast protests: Diplomat says Libya long thought Gadha crazy 21 Feb 2011 : N. Africa, Mideast protests Gadha : I'm still here 23 Feb 2011 : N. Africa, Mideast protests: Libya's interior minister kidnapped, media say 27 Feb 2011 : N. Africa, Mideast protests: Egyptian stock market set to reopen Tuesday k k-1