Searching for relevant text documents has traditionally been based on keywords and Boolean expressions of them. Often the search results show high recall and low precision, or vice versa. Considerable efforts have been made to develop alternative methods, but their practical applicability has been low. Powerful methods are needed for the exploration of miscellaneous document collections. The WEBSOM method organizes a document collection on a map display that provides an overview of the collection and facilitates interactive browsing. Interesting documents can be retrieved by a content addressable search of interesting map locations. The interesting locations could also be marked as filters for collecting interesting new documents.

The explosive growth in the availability of information is overwhelming traditional information management systems. Although individual pieces of information have become easy to find, the larger context in which they exist has become harder to track. These contextual questions are ideally suited to visualization since the humrex visual system is remarkably adept at interpreting large quantities of information, and at detecting patterns and anomalies. The challenge is to present the information in a manner that maximally leverages our v/sual skills. This paper discusses a set of properties that such a presentation should have, and describes the design and functionality of Vxlnsight, a visualization tool built to these principles.

AB AB AB Org IN AF AD Source JN SO SO Year parse from PB PY DP Type DT PT PT Title TI TI TI Author AU AU AU Terms DE DE MH Table 3. Number of articles kept from each data source in combined data set.

We discuss the implementation of a cartographic user interface to bibliographic and other information subspaces in astronomy. This includes a front-end to two of the ve premier scholarly journals in astronomy. We present a range of comparative assessments, in operational frameworks, of this approach to accessing and retrieving astronomical information. Finally we discuss the particular role that such cartographic user interfaces can play in Web-based information seeking, and contrast this with widely-used currently available search technologies. Keywords: Concept spaces, Distributed information retrieval, Information Author for correspondence. Email f.murtagh@qub.ac.uk 1 seeking, Internet, Kohonen self-organizing feature maps, Maps, Neural networks, Resource discovery, User interfaces 1 Introduction Information retrieval by means of \semantic road maps" was rst detailed by Doyle (1961). The spatial metaphor is a very powerful one in human information processing. The sp...

This paper examines the problems inherent in navigating the World-Wide Web. It discusses the work done by others in crafting techniques, software products, and research prototypes that attempt to improve the browsing experience through the application of information visualization in the form of sitemaps. This paper also describes an animated technique to generate previews and overviews of a web site in order to get a better understanding of its contents. The final section includes a technical description of an early prototype tool that uses this animated technique, with preliminary findings from an informal feasibility study involving 19 subjects. Keywords Web browsing; alternative user interfaces; web navigation; previews; overviews; web crawler; searching Context and Problem Statement The World-Wide Web is a constantly evolving maze of HTML, DHTML, XML, Java, JavaScript, CGI, Active Server Pages, Shockwave, Flash, and other means of generating hypertext content. It is an extremely ...

This paper discusses several data mining algorithms and techniques that we have developed at the University of Arizona Artificial Intelligence Lab. We have implemented these algorithms and techniques into several prototypes, one of which focuses on medical information developed in cooperation with the National Cancer Institute (NCI) and the University of Illinois at Urbana-Champaign. We propose an architecture for medical knowledge information systems that will permit data mining across several medical information sources and discuss a suite of data mining tools that we are developing to assist NCI in improving public access to and use of their existing vast cancer information collections.

We present the application of a new knowledge visualization tool, VxInsight, to the mapping and analysis of patent databases. Patent data are mined and placed in a database, relationships between the patents are identified, primarily using the citation and classification structures, then the patents are clustered using a proprietary force-directed placement algorithm. Related patents cluster together to produce a 3-D landscape view of the tens of thousands of patents. The user can navigate the landscape by zooming into or out of regions of interest. Querying the underlying database places a colored marker on each patent matching the query. Automatically generated labels, showing landscape content, update continually upon zooming. Optionally, citation links between patents may be shown on the landscape. The combination of these features enables powerful analyses of patent databases.

While the breath of vocabulary used in long documents may mislead the traditional keyword-based retrieval systems, the demands for techniques in nontextual Web classification and retrieval from a large document collection are mounting. Only a few prototype systems have attempted to classify hypertext on the basis of nontextual elements in order to locate unfamiliar documents. As a result, a large portion of Web documents having pictorial information in nature is far beyond the reach of most current search engines. In this research, we devise a novel quantitative model of nontextual World Wide Web (WWW) classification based on image information. An intelligent content-sensitive, attribute-rich image classifier is presented. An image similarity measure is used to deduce the likelihood among images. Different image feature vectors have been constructed and evaluated. Evaluation shows images judged to be similar by human form interesting clusters in our unsupervised learning. Comparison with other clustering technique, such as Hierarchical Agglomerative Clustering (HAC), demonstrates that our approach is found useful in content-based image information retrieval.

Digital libraries stand to benefit from technology insertions from the fields of information visualization, human-computer interaction, and cognitive psychology, among others. However, the current state of interaction between these fields is not well understood. We use our knowledge visualization tool, VxInsight , to provide several domain visualizations of the overlap between these fields. Relevant articles were extracted from the Science Citation Indexes (SCI and Social SCI) using keyword searches. An article map, a semantic (co-term) map, and a co-author network have been generated from the data. Analysis reveals that while there are overlaps between fields, they are not substantial. However, the most recent work suggests areas where future collaboration could have a great impact on digital libraries of the future.

An approach to automatic modeling of text documents is presented, where `semantic features' based on contextual dependencies are extracted from the textual data. The model structure has two levels first, context categories are constructed using sentences in the documents as elementary contextual units, and, second, document categories are constructed using the lower-level document analysis results as input data. Models on both of these levels are based on a feature extraction scheme, where the features can be interpreted as coordinate axes in the linear high-dimensional space. The models are adaptive, being updated according to what kind of documents have been read, so that the user-specific `profile' helps to find relevant documents that match the user's personal model. An implementation of this approach is presented, technical details are discussed, and some results when using the program are reviewed.