Tracking and modelling information diffusion across interactive online media

Abstract

Information spreads rapidly across Web sites, Web logs and online forums. This paper describes the research framework of the IDIOM Project (Information Diffusion across Interactive Online Media), 1 which analyzes this process by identifying redundant content elements, mapping them to an ontological knowledge structure, and tracking their temporal and geographic distribution. Linguists define "idiom" as an expression whose meaning is different from the literal meanings of its component words. Similarly, the study of information diffusion promises insights that cannot be inferred from individual network elements. This paper presents underlying technology, initial results, and the future roadmap of investigating information diffusion based on ontological knowledge structures. Similar projects often focus on particular media, or neglect important aspects of the human language. This paper addresses these gaps to reveal fundamental mechanisms of information diffusion across media with distinct interactive characteristics.

Optimizing queries to remote resources

“…The simulations use two weekly snapshots from the IDIOM Media Watch on Climate Change (Hubmann-Haidvogel et al, 2009;Scharl et al, 2007) database comprising approximately one million documents. The IDIOM Media Watch on Climate Change's media corpus draws upon a list of 156 news media sites from five English-speaking countries (Liu et al, 2005).…”

“…Large-scale Semantic Web projects such as the IDIOM Media Watch on Climate Change (Hubmann-Haidvogel et al, 2009;Scharl et al, 2007), which process hundreds of thousands of pages a week, demonstrate the importance of these guidelines. Querying GeoNames to geo-tag all the documents mirrored by IDIOM's architecture would add days of processing time.…”

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

“…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.…”

Applying Optimal Stopping for Optimizing Queries to External Semantic Web Resources

“…Large scale Semantic Web projects, like the IDIOM media watch on climate change [11], process hundred thousands of pages a week. Querying GeoNames for geo-tagging such numbers of documents would add days of processing time to the IDIOM architecture.…”