Search (21 results, page 1 of 2)

0.008447195 = product of:
  0.042235978 = sum of:
    0.042235978 = product of:
      0.084471956 = sum of:
        0.084471956 = weight(_text_:data in 3195) [ClassicSimilarity], result of:
          0.084471956 = score(doc=3195,freq=16.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.5928845 = fieldWeight in 3195, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.046875 = fieldNorm(doc=3195)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

The scientific community's growing eagerness to make research data available to the public provides libraries - with our expertise in metadata and discovery - an interesting new opportunity. This paper details the in-house creation of a "data catalog" which describes datasets ranging from population-level studies like the US Census to small, specialized datasets created by researchers at our own institution. Based on Symfony2 and Solr, the data catalog provides a powerful search interface to help researchers locate the data that can help them, and an administrative interface so librarians can add, edit, and manage metadata elements at will. This paper will outline the successes, failures, and total redos that culminated in the current manifestation of our data catalog.

0.007544966 = product of:
  0.03772483 = sum of:
    0.03772483 = weight(_text_:bibliographic in 3869) [ClassicSimilarity], result of:
      0.03772483 = score(doc=3869,freq=2.0), product of:
        0.17541347 = queryWeight, product of:
          3.893044 = idf(docFreq=2449, maxDocs=44218)
          0.04505818 = queryNorm
        0.21506234 = fieldWeight in 3869, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.893044 = idf(docFreq=2449, maxDocs=44218)
          0.0390625 = fieldNorm(doc=3869)
  0.2 = coord(1/5)

0.0074663362 = product of:
  0.03733168 = sum of:
    0.03733168 = product of:
      0.07466336 = sum of:
        0.07466336 = weight(_text_:data in 3888) [ClassicSimilarity], result of:
          0.07466336 = score(doc=3888,freq=18.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.52404076 = fieldWeight in 3888, product of:
              4.2426405 = tf(freq=18.0), with freq of:
                18.0 = termFreq=18.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3888)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

We present a new technique called "t-SNE" that visualizes high-dimensional data by giving each datapoint a location in a two or three-dimensional map. The technique is a variation of Stochastic Neighbor Embedding (Hinton and Roweis, 2002) that is much easier to optimize, and produces significantly better visualizations by reducing the tendency to crowd points together in the center of the map. t-SNE is better than existing techniques at creating a single map that reveals structure at many different scales. This is particularly important for high-dimensional data that lie on several different, but related, low-dimensional manifolds, such as images of objects from multiple classes seen from multiple viewpoints. For visualizing the structure of very large data sets, we show how t-SNE can use random walks on neighborhood graphs to allow the implicit structure of all of the data to influence the way in which a subset of the data is displayed. We illustrate the performance of t-SNE on a wide variety of data sets and compare it with many other non-parametric visualization techniques, including Sammon mapping, Isomap, and Locally Linear Embedding. The visualizations produced by t-SNE are significantly better than those produced by the other techniques on almost all of the data sets.

Theme

Data Mining

0.007315486 = product of:
  0.03657743 = sum of:
    0.03657743 = product of:
      0.07315486 = sum of:
        0.07315486 = weight(_text_:data in 3884) [ClassicSimilarity], result of:
          0.07315486 = score(doc=3884,freq=12.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.513453 = fieldWeight in 3884, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.046875 = fieldNorm(doc=3884)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

Techniques for multidimensional scaling visualize objects as points in a low-dimensional metric map. As a result, the visualizations are subject to the fundamental limitations of metric spaces. These limitations prevent multidimensional scaling from faithfully representing non-metric similarity data such as word associations or event co-occurrences. In particular, multidimensional scaling cannot faithfully represent intransitive pairwise similarities in a visualization, and it cannot faithfully visualize "central" objects. In this paper, we present an extension of a recently proposed multidimensional scaling technique called t-SNE. The extension aims to address the problems of traditional multidimensional scaling techniques when these techniques are used to visualize non-metric similarities. The new technique, called multiple maps t-SNE, alleviates these problems by constructing a collection of maps that reveal complementary structure in the similarity data. We apply multiple maps t-SNE to a large data set of word association data and to a data set of NIPS co-authorships, demonstrating its ability to successfully visualize non-metric similarities.

Theme

Data Mining

0.0066034766 = product of:
  0.033017382 = sum of:
    0.033017382 = product of:
      0.066034764 = sum of:
        0.066034764 = weight(_text_:data in 79) [ClassicSimilarity], result of:
          0.066034764 = score(doc=79,freq=22.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.46347913 = fieldWeight in 79, product of:
              4.690416 = tf(freq=22.0), with freq of:
                22.0 = termFreq=22.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.03125 = fieldNorm(doc=79)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

With the terrific growth of data volume and data being produced every second on millions of devices across the globe, there is a desperate need to manage the unstructured data available on web pages efficiently. Semantic Web or also known as Web of Trust structures the scattered data on the Internet according to the needs of the user. It is an extension of the World Wide Web (WWW) which focuses on manipulating web data on behalf of Humans. Due to the ability of the Semantic Web to integrate data from disparate sources and hence makes it more user-friendly, it is an emerging trend. Tim Berners-Lee first introduced the term Semantic Web and since then it has come a long way to become a more intelligent and intuitive web. Data Visualization plays an essential role in explaining complex concepts in a universal manner through pictorial representation, and the Semantic Web helps in broadening the potential of Data Visualization and thus making it an appropriate combination. The objective of this chapter is to provide fundamental insights concerning the semantic web technologies and in addition to that it also elucidates the issues as well as the solutions regarding the semantic web. The purpose of this chapter is to highlight the semantic web architecture in detail while also comparing it with the traditional search system. It classifies the semantic web architecture into three major pillars i.e. RDF, Ontology, and XML. Moreover, it describes different semantic web tools used in the framework and technology. It attempts to illustrate different approaches of the semantic web search engines. Besides stating numerous challenges faced by the semantic web it also illustrates the solutions.

Series

Lecture notes on data engineering and communications technologies book series; vol.32

Source

Data visualization and knowledge engineering. Eds. J. Hemanth, et al

0.006035973 = product of:
  0.030179864 = sum of:
    0.030179864 = weight(_text_:bibliographic in 2547) [ClassicSimilarity], result of:
      0.030179864 = score(doc=2547,freq=2.0), product of:
        0.17541347 = queryWeight, product of:
          3.893044 = idf(docFreq=2449, maxDocs=44218)
          0.04505818 = queryNorm
        0.17204987 = fieldWeight in 2547, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.893044 = idf(docFreq=2449, maxDocs=44218)
          0.03125 = fieldNorm(doc=2547)
  0.2 = coord(1/5)

Abstract

The discovery service (a search engine and service called WILBERT) used at our library at the Technical University of Applied Sciences Wildau (TUAS Wildau) is comprised of more than 8 million items. If we were to record all licensed publications in this tool to a higher level of articles, including their bibliographic records and full texts, we would have a holding estimated at a hundred million documents. A lot of features, such as ranking, autocompletion, multi-faceted classification, refining opportunities reduce the number of hits. However, it is not enough to give intuitive support for a systematic overview of topics related to documents in the library. John Naisbitt once said: "We are drowning in information, but starving for knowledge." This quote is still very true today. Two years ago, we started to develop micro thesauri for MINT topics in order to develop an advanced indexing of the library stock. We use iQvoc as a vocabulary management system to create the thesaurus. It provides an easy-to-use browser interface that builds a SKOS thesaurus in the background. The purpose of this is to integrate the thesauri in WILBERT in order to offer a better subject-related search. This approach especially supports first-year students by giving them the possibility to browse through a hierarchical alignment of a subject, for instance, logistics or computer science, and thereby discover how the terms are related. It also supports the students with an insight into established abbreviations and alternative labels. Students at the TUAS Wildau were involved in the developmental process of the software regarding the interface and functionality of iQvoc. The first steps have been taken and involve the inclusion of 3000 terms in our discovery tool WILBERT.

0.006034968 = product of:
  0.03017484 = sum of:
    0.03017484 = product of:
      0.06034968 = sum of:
        0.06034968 = weight(_text_:data in 3883) [ClassicSimilarity], result of:
          0.06034968 = score(doc=3883,freq=6.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.42357713 = fieldWeight in 3883, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.0546875 = fieldNorm(doc=3883)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

The paper presents a new unsupervised dimensionality reduction technique, called parametric t-SNE, that learns a parametric mapping between the high-dimensional data space and the low-dimensional latent space. Parametric t-SNE learns the parametric mapping in such a way that the local structure of the data is preserved as well as possible in the latent space. We evaluate the performance of parametric t-SNE in experiments on three datasets, in which we compare it to the performance of two other unsupervised parametric dimensionality reduction techniques. The results of experiments illustrate the strong performance of parametric t-SNE, in particular, in learning settings in which the dimensionality of the latent space is relatively low.

Theme

Data Mining

0.006034968 = product of:
  0.03017484 = sum of:
    0.03017484 = product of:
      0.06034968 = sum of:
        0.06034968 = weight(_text_:data in 3886) [ClassicSimilarity], result of:
          0.06034968 = score(doc=3886,freq=6.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.42357713 = fieldWeight in 3886, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.0546875 = fieldNorm(doc=3886)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

The paper investigates the acceleration of t-SNE-an embedding technique that is commonly used for the visualization of high-dimensional data in scatter plots-using two tree-based algorithms. In particular, the paper develops variants of the Barnes-Hut algorithm and of the dual-tree algorithm that approximate the gradient used for learning t-SNE embeddings in O(N*logN). Our experiments show that the resulting algorithms substantially accelerate t-SNE, and that they make it possible to learn embeddings of data sets with millions of objects. Somewhat counterintuitively, the Barnes-Hut variant of t-SNE appears to outperform the dual-tree variant.

Theme

Data Mining

0.0056314636 = product of:
  0.028157318 = sum of:
    0.028157318 = product of:
      0.056314636 = sum of:
        0.056314636 = weight(_text_:data in 3887) [ClassicSimilarity], result of:
          0.056314636 = score(doc=3887,freq=4.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.3952563 = fieldWeight in 3887, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.0625 = fieldNorm(doc=3887)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

Although extremely useful for visualizing high-dimensional data, t-SNE plots can sometimes be mysterious or misleading. By exploring how it behaves in simple cases, we can learn to use it more effectively. We'll walk through a series of simple examples to illustrate what t-SNE diagrams can and cannot show. The t-SNE technique really is useful-but only if you know how to interpret it.

Theme

Data Mining

0.005565079 = product of:
  0.027825395 = sum of:
    0.027825395 = product of:
      0.05565079 = sum of:
        0.05565079 = weight(_text_:data in 3870) [ClassicSimilarity], result of:
          0.05565079 = score(doc=3870,freq=10.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.39059696 = fieldWeight in 3870, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3870)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

Data from multiple knowledge organization systems are combined to provide a global overview of the content holdings of a small personal library. Subject headings and classification data are used to effectively map the combined book and topic space of the library. While harvested and manipulated by hand, the work reveals issues and potential solutions when using automated techniques to produce topic maps of much larger libraries. The small library visualized consists of the thirty-nine, digital, English language books found in the Osama Bin Laden (OBL) compound in Abbottabad, Pakistan upon his death. As this list of books has garnered considerable media attention, it is worth providing a visual overview of the subject content of these books - some of which is not readily apparent from the titles. Metadata from subject headings and classification numbers was combined to create book-subject maps. Tree maps of the classification data were also produced. The books contain 328 subject headings. In order to enhance the base map with meaningful thematic overlay, library holding count data was also harvested (and aggregated from duplicates). This additional data revealed the relative scarcity or popularity of individual books.

0.0045269798 = product of:
  0.022634897 = sum of:
    0.022634897 = weight(_text_:bibliographic in 1197) [ClassicSimilarity], result of:
      0.022634897 = score(doc=1197,freq=2.0), product of:
        0.17541347 = queryWeight, product of:
          3.893044 = idf(docFreq=2449, maxDocs=44218)
          0.04505818 = queryNorm
        0.1290374 = fieldWeight in 1197, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.893044 = idf(docFreq=2449, maxDocs=44218)
          0.0234375 = fieldNorm(doc=1197)
  0.2 = coord(1/5)

0.003982046 = product of:
  0.01991023 = sum of:
    0.01991023 = product of:
      0.03982046 = sum of:
        0.03982046 = weight(_text_:data in 4743) [ClassicSimilarity], result of:
          0.03982046 = score(doc=4743,freq=2.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.2794884 = fieldWeight in 4743, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.0625 = fieldNorm(doc=4743)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

In this paper, we describe in detail the Information Content Evaluation Map (ICE-Map Visualization, formerly referred to as IC Difference Analysis). The ICE-Map Visualization is a visual data mining approach for all kinds of concept hierarchies that uses statistics about the concept usage to help a user in the evaluation and maintenance of the hierarchy. It consists of a statistical framework that employs the the notion of information content from information theory, as well as a visualization of the hierarchy and the result of the statistical analysis by means of a treemap.

0.0036628568 = product of:
  0.018314283 = sum of:
    0.018314283 = product of:
      0.036628567 = sum of:
        0.036628567 = weight(_text_:22 in 1289) [ClassicSimilarity], result of:
          0.036628567 = score(doc=1289,freq=2.0), product of:
            0.15778607 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.04505818 = queryNorm
            0.23214069 = fieldWeight in 1289, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.046875 = fieldNorm(doc=1289)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Content

Vortrag anlässlich des Workshops: "Extending the multilingual capacity of The European Library in the EDL project Stockholm, Swedish National Library, 22-23 November 2007".

0.0029865343 = product of:
  0.014932672 = sum of:
    0.014932672 = product of:
      0.029865343 = sum of:
        0.029865343 = weight(_text_:data in 919) [ClassicSimilarity], result of:
          0.029865343 = score(doc=919,freq=2.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.2096163 = fieldWeight in 919, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.046875 = fieldNorm(doc=919)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

Document retrieval is a highly interactive process dealing with large amounts of information. Visual representations can provide both a means for managing the complexity of large information structures and an interface style well suited to interactive manipulation. The system we have designed utilizes visually displayed graphic structures and a direct manipulation interface style to supply an integrated environment for retrieval. A common visually displayed network structure is used for query, document content, and term relations. A query can be modified through direct manipulation of its visual form by incorporating terms from any other information structure the system displays. An associative thesaurus of terms and an inter-document network provide information about a document collection that can complement other retrieval aids. Visualization of these large data structures makes use of fisheye views and overview diagrams to help overcome some of the inherent difficulties of orientation and navigation in large information structures.

0.0029865343 = product of:
  0.014932672 = sum of:
    0.014932672 = product of:
      0.029865343 = sum of:
        0.029865343 = weight(_text_:data in 1293) [ClassicSimilarity], result of:
          0.029865343 = score(doc=1293,freq=2.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.2096163 = fieldWeight in 1293, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.046875 = fieldNorm(doc=1293)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

This paper aims to identify what information visualisation is and how in conjunction with the computer it can be used as a tool to expand understanding. It also seeks to explain how information visualisation has been fundamental to the development of the computer from its very early days to Apple's launch of the now ubiquitous W.I.M.P (Windows, Icon, Menu, Program) graphical user interface in 1984. An attempt is also made to question why after many years of progress and development though the late 1960s and 1970s, very little has changed in the way we interact with the data on our computers since the watershed of the Macintosh and in conclusion where the future of information visualisation may lie.

0.0029865343 = product of:
  0.014932672 = sum of:
    0.014932672 = product of:
      0.029865343 = sum of:
        0.029865343 = weight(_text_:data in 2906) [ClassicSimilarity], result of:
          0.029865343 = score(doc=2906,freq=2.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.2096163 = fieldWeight in 2906, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.046875 = fieldNorm(doc=2906)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

The use of research impact metrics and analytics has become an integral component to many aspects of institutional assessment. Many platforms currently exist to provide such analytics, both proprietary and open source; however, the functionality of these systems may not always overlap to serve uniquely specific needs. In this paper, I describe a novel web-based platform, named Manifold, that I built to serve custom research impact assessment needs in the University of Minnesota Medical School. Built on a standard LAMP architecture, Manifold automatically pulls publication data for faculty from Scopus through APIs, calculates impact metrics through automated analytics, and dynamically generates report-like profiles that visualize those metrics. Work on this project has resulted in many lessons learned about challenges to sustainability and scalability in developing a system of such magnitude.

0.0029865343 = product of:
  0.014932672 = sum of:
    0.014932672 = product of:
      0.029865343 = sum of:
        0.029865343 = weight(_text_:data in 3205) [ClassicSimilarity], result of:
          0.029865343 = score(doc=3205,freq=2.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.2096163 = fieldWeight in 3205, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.046875 = fieldNorm(doc=3205)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Theme

Data Mining

0.0029865343 = product of:
  0.014932672 = sum of:
    0.014932672 = product of:
      0.029865343 = sum of:
        0.029865343 = weight(_text_:data in 3867) [ClassicSimilarity], result of:
          0.029865343 = score(doc=3867,freq=2.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.2096163 = fieldWeight in 3867, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.046875 = fieldNorm(doc=3867)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

An event is a specific occurrence involving participants, which is a typed, n-ary association of entities or other events, each identified as a participant in a specific semantic role in the event (Pyysalo et al. 2012; Linguistic Data Consortium 2005). Event types may vary across domains. Representing relationships between events can facilitate the understanding of knowledge in complex systems (such as economic systems, human body, social systems). In the simplest form, an event can be represented as Entity A <Relation> Entity B. This paper evaluates several knowledge organization and visualization models and tools, such as concept maps (Cmap), topic maps (Ontopia), network analysis models (Gephi), and ontology (Protégé), then proposes an event relationship model that aims to integrate the strengths of these models, and can represent complex knowledge expressed in events and their relationships.

0.0028157318 = product of:
  0.014078659 = sum of:
    0.014078659 = product of:
      0.028157318 = sum of:
        0.028157318 = weight(_text_:data in 1292) [ClassicSimilarity], result of:
          0.028157318 = score(doc=1292,freq=4.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.19762816 = fieldWeight in 1292, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.03125 = fieldNorm(doc=1292)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Content

Traditional print reference guides often have two methods of finding information: an order (alphabetical for dictionaries and encyclopedias, by subject hierarchy in the case of thesauri) and indices (ordered lists, with a more complete listing of words and concepts, which refers back to original content from the main body of the book). A user of such traditional print reference guides who is looking for information will either browse through the ordered information in the main body of the reference book, or scan through the indices to find what is necessary. The advent of the computer allows for much more rapid electronic searches of the same information, and for multiple layers of indices. Users can either search through information by entering a keyword, or users can browse through the information through an outline index, which represents the information contained in the main body of the data. There are two traditional user interfaces for such applications. First, the user may type text into a search field and in response, a list of results is returned to the user. The user then selects a returned entry and may page through the resulting information. Alternatively, the user may choose from a list of words from an index. For example, software thesaurus applications, in which a user attempts to find synonyms, antonyms, homonyms, etc. for a selected word, are usually implemented using the conventional search and presentation techniques discussed above. The presentation of results only allows for a one-dimensional order of data at any one time. In addition, only a limited number of results can be shown at once, and selecting a result inevitably leads to another page-if the result is not satisfactory, the users must search again. Finally, it is difficult to present information about the manner in which the search results are related, or to present quantitative information about the results without causing confusion. Therefore, there exists a need for a multidimensional graphical display of information, in particular with respect to information relating to the meaning of words and their relationships to other words. There further exists a need to present large amounts of information in a way that can be manipulated by the user, without the user losing his place. And there exists a need for more fluid, intuitive and powerful thesaurus functionality that invites the exploration of language.

0.0024887787 = product of:
  0.012443894 = sum of:
    0.012443894 = product of:
      0.024887787 = sum of:
        0.024887787 = weight(_text_:data in 3366) [ClassicSimilarity], result of:
          0.024887787 = score(doc=3366,freq=2.0), product of:
            0.14247625 = queryWeight, product of:
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.04505818 = queryNorm
            0.17468026 = fieldWeight in 3366, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.1620505 = idf(docFreq=5088, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3366)
      0.5 = coord(1/2)
  0.2 = coord(1/5)

Abstract

Documents in rich text corpora usually contain multiple facets of information. For example, an article about a specific disease often consists of different facets such as symptom, treatment, cause, diagnosis, prognosis, and prevention. Thus, documents may have different relations based on different facets. Powerful search tools have been developed to help users locate lists of individual documents that are most related to specific keywords. However, there is a lack of effective analysis tools that reveal the multifaceted relations of documents within or cross the document clusters. In this paper, we present FacetAtlas, a multifaceted visualization technique for visually analyzing rich text corpora. FacetAtlas combines search technology with advanced visual analytical tools to convey both global and local patterns simultaneously. We describe several unique aspects of FacetAtlas, including (1) node cliques and multifaceted edges, (2) an optimized density map, and (3) automated opacity pattern enhancement for highlighting visual patterns, (4) interactive context switch between facets. In addition, we demonstrate the power of FacetAtlas through a case study that targets patient education in the health care domain. Our evaluation shows the benefits of this work, especially in support of complex multifaceted data analysis.