Multiple coordinated views for searching and navigating Web content repositories

Abstract

The advantages and positive effects of multiple coordinated views on search performance have been documented in several studies. This paper describes the implementation of multiple coordinated views within the Media Watch on Climate Change, a domain-specific news aggregation portal available at www.ecoresearch.net/climate that combines a portfolio of semantic services with a visual information exploration and retrieval interface. The system builds contextualized information spaces by enriching the content repository with geospatial, semantic and temporal annotations, and by applying semi-automated ontology learning to create a controlled vocabulary for structuring the stored information. Portlets visualize the different dimensions of the contextualized information spaces, providing the user with multiple views on the latest news media coverage. Context information facilitates access to complex datasets and helps users navigate large repositories of Web documents. Currently, the system synchronizes information landscapes, domain ontologies, geographic maps, tag clouds and just-in-time information retrieval agents that suggest similar topics and nearby locations.

Dynamic Topography Information Landscapes – An Incremental Approach to Visual Knowledge Discovery

“…For evaluating the incremental computation framework we computed ten consecutive landscapes for 2000 documents from the environmental blog data set of the Media Watch on Climate Change [16], a Web content aggregator about climate change and related environmental issues that serves static versions of the information landscapes presented in this paper as part of a multiple coordinated view representation. Each week new documents are gathered via the webLyzard crawler.…”

“…Prior to the beginning of the computation, the raw textual data to be analyzed is gathered via a web crawler, then converted and annotated into the content repositories based on previous research [16], [32]. We utilize our experiences with webLyzard, an established and scalable media monitoring and Web intelligence platform (www.weblyzard.com), to generate the document keyword relevance table (1A) and the document word frequency table (1B).…”

“…A chi-square test of significance with Yates' correction determines over-represented terms. The term co-occurrence analysis, based on pattern matching algorithm, along with trigger phrases based on regular expressions, is used to identify the frequently appearing text fragments within the same sentences and within the documents [16], [32]. The redundancy of nouns' singular and plural forms and synonyms in the resultant list of labels are removed by using a combination of regular expression queries and WordNet library lookup.…”

“…In addition, we evaluate our incremental computation framework by comparing stress values between incrementally and non-incrementally computed layouts. Documents for these experiments are taken from the environmental blog sample of the Media Watch on Climate Change [16], a Web content aggregator on climate change and related environmental issues. Our experimental results show that the incremental computation approach yields not only comparable, but even slightly better stress values and thereby indicate our framework's validity.…”

Visualizing Contextual Information in Aggregated Web Content Repositories

“…Media analytics solutions have been developed for various domains including sports [6], politics [2; 9] and climate change [4; 8], often focusing on specific aspects such as (sub-)event detection [1], content classification [4] and the automated annotation of video broadcasts [2]. Such media analytics systems face two major challenges:…”