BackgroundWe investigate the accuracy of different similarity approaches for clustering over two million biomedical documents. Clustering large sets of text documents is important for a variety of information needs and applications such as collection management and navigation, summary and analysis. The few comparisons of clustering results from different similarity approaches have focused on small literature sets and have given conflicting results. Our study was designed to seek a robust answer to the question of which similarity approach would generate the most coherent clusters of a biomedical literature set of over two million documents.MethodologyWe used a corpus of 2.15 million recent (2004-2008) records from MEDLINE, and generated nine different document-document similarity matrices from information extracted from their bibliographic records, including titles, abstracts and subject headings. The nine approaches were comprised of five different analytical techniques with two data sources. The five analytical techniques are cosine similarity using term frequency-inverse document frequency vectors (tf-idf cosine), latent semantic analysis (LSA), topic modeling, and two Poisson-based language models – BM25 and PMRA (PubMed Related Articles). The two data sources were a) MeSH subject headings, and b) words from titles and abstracts. Each similarity matrix was filtered to keep the top-n highest similarities per document and then clustered using a combination of graph layout and average-link clustering. Cluster results from the nine similarity approaches were compared using (1) within-cluster textual coherence based on the Jensen-Shannon divergence, and (2) two concentration measures based on grant-to-article linkages indexed in MEDLINE.ConclusionsPubMed's own related article approach (PMRA) generated the most coherent and most concentrated cluster solution of the nine text-based similarity approaches tested, followed closely by the BM25 approach using titles and abstracts. Approaches using only MeSH subject headings were not competitive with those based on titles and abstracts.

No abstract

No abstract

From an informed critique of existing methods to the development of original tools, cartographic engagement can provide a unique perspective on knowledge domain visualization. Along with a discussion of some principles underlying a cartographically informed visualization methodology, results of experiments involving several thousand conference abstracts will be sketched and their plausibility reflected on.

In recent years, the proliferation of multi-temporal census data products and the increased capabilities of geospatial analysis and visualization techniques have encouraged longitudinal analyses of socioeconomic census data. Traditional cartographic methods for illustrating socioeconomic change tend to rely either on comparison of multiple temporal snapshots or on explicit representation of the magnitude of change occurring between different time periods. This paper proposes to add another perspective to the visualization of temporal change, by linking multi-temporal observations to a geometric configuration that is not based on geographic space, but on a spatialized representation of n-dimensional attribute space. The presented methodology aims at providing a cognitively plausible representation of changes occurring inside census areas by representing their attribute space trajectories as line features traversing a two-dimensional display space. First, the self-organizing map (SOM) method is used to transform n-dimensional data such that the resulting two-dimensional configuration can be represented with standard GIS data structures. Then, individual census observations are mapped onto the neural network and linked as temporal vertices to represent attribute space trajectories as directed graphs. This method is demonstrated for a data set containing 254 counties and 32 demographic variables. Various transformations and visual results are presented and discussed in the paper, from the visualization of individual component planes and trajectory clusters to the mapping of different attributes onto temporal trajectories.