In the past several years studies have started to appear comparing the accuracies of various science mapping approaches. These studies primarily compare the cluster solutions resulting from different similarity approaches, and give varying results. In this study we compare the accuracies of cluster solutions of a large corpus of 2,153,769 recent articles from the biomedical literature (2004-2008) using four similarity approaches: co-citation analysis, bibliographic coupling, direct citation, and a bibliographic coupling-based citation-text hybrid approach. Each of the four approaches can be considered a way to represent the research front in biomedicine, and each is able to successfully cluster over 92% of the corpus. Accuracies are compared using two metrics-within-cluster textual coherence as defined by the Jensen-Shannon divergence, and a concentration measure based on the grant-to-article linkages indexed in MEDLINE. Of the three pure citation-based approaches, bibliographic coupling slightly outperforms co-citation analysis using both accuracy measures; direct citation is the least accurate mapping approach by far. The hybrid approach improves upon the bibliographic coupling results in all respects. We consider the results of this study to be robust given the very large size of the corpus, and the specificity of the accuracy measures used. IntroductionScience mapping has reached the point where it is no longer a primarily academic venture but instead is being driven by and used for practical purposes. Although such mapping is often equated with visual representations of the structure of science, the visuals are only a reflection of the layout and partitioning of bibliographic units (e.g., documents, words, authors, journals) that are the primary output of the mathematics behind the mapping. The partitions themselves, along with detailed analysis of the partitions, are typically of far more interest to decision-makers than are visuals of the structure. The accuracy of these partitions becomes very important, especially when these maps are used for real-world problems of research planning and evaluation.Our work over the past several years has been aimed specifically at creating ever more detailed (Klavans & Boyack, 2010) We recently completed a study for the U.S. National Institutes of Health (NIH) in which we compared science maps generated from a single large corpus (2.15 million documents published from 2004-2008) using 13 different similarity approaches, including three citation-based approaches, nine text-based approaches, and one hybrid approach. The ultimate application of this science mapping effort for the NIH will be for portfolio planning and analysis; any time science mapping has the potential to become commingled with funding and decision making, the map must be as accurate as possible. Thus, our study was focused on determining how to generate the most accurate large-scale map of the medical science literature for portfolio analysis applications.In any study of accuracy, the question of how to m...

This paper presents a new map representing the structure of all of science, based on journal articles, including both the natural and social sciences. Similar to cartographic maps of our world, the map of science provides a bird's eye view of today's scientific landscape. It can be used to visually identify major areas of science, their size, similarity, and interconnectedness. In order to be useful, the map needs to be accurate on a local and on a global scale. While our recent work has focused on the former aspect, 1 this paper summarizes results on how to achieve structural accuracy.Eight alternative measures of journal similarity were applied to a data set of 7,121 journals covering over 1 million documents in the combined Science Citation and Social Science Citation Indexes. For each journal similarity measure we generated two-dimensional spatial layouts using the force-directed graph layout tool, VxOrd. Next, mutual information values were calculated for each graph at different clustering levels to give a measure of structural accuracy for each map. The best co-citation and inter-citation maps according to local and structural accuracy were selected and are presented and characterized. These two maps are compared to establish robustness. The inter-citation map is then used to examine linkages between disciplines. Biochemistry appears as the most interdisciplinary discipline in science.

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.

In 1965, Price foresaw the day when a citation‐based taxonomy of science and technology would be delineated and correspondingly used for science policy. A taxonomy needs to be comprehensive and accurate if it is to be useful for policy making, especially now that policy makers are utilizing citation‐based indicators to evaluate people, institutions and laboratories. Determining the accuracy of a taxonomy, however, remains a challenge. Previous work on the accuracy of partition solutions is sparse, and the results of those studies, although useful, have not been definitive. In this study we compare the accuracies of topic‐level taxonomies based on the clustering of documents using direct citation, bibliographic coupling, and co‐citation. Using a set of new gold standards—articles with at least 100 references—we find that direct citation is better at concentrating references than either bibliographic coupling or co‐citation. Using the assumption that higher concentrations of references denote more accurate clusters, direct citation thus provides a more accurate representation of the taxonomy of scientific and technical knowledge than either bibliographic coupling or co‐citation. We also find that discipline‐level taxonomies based on journal schema are highly inaccurate compared to topic‐level taxonomies, and recommend against their use.

No abstract