Clustering More than Two Million Biomedical Publications: Comparing the Accuracies of Nine Text-Based Similarity Approaches
PLoS ONEPublished 17 March 2011Open access
Kevin W. Boyack, David Newman, Russell J. Duhon, Richard Klavans, Michael Patek, Joseph R. Biberstine
Citations282
SJR quartileQ1
SJR score0.80
SNIP1.07
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
PubMed Related Articles' 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.
Abstract
PubMed'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.
Keywords
Computer ScienceBiochemistry, Genetics and Molecular Biology
Journal of Machine Learning ResearchLatent dirichlet allocation
27,049 Citations2003David M. Blei, Andrew Y. Ng +1 more
Journal of the American Society for Information ScienceIndexing by latent semantic analysis
12,677 Citations1990Scott Deerwester, Susan Dumais +3 more
Springer series in information sciencesSelf-Organizing Maps
10,377 Citations1997Teuvo Kohonen
The mathematical preliminaries, background, basic ideas, and implications of the Self-Organising Map algorithm are expounded in a manner which is accessible without prior expert knowledge.
Information Processing & ManagementTerm-weighting approaches in automatic text retrieval
9,532 Citations1988Gerard Salton, Chris Buckley
This paper summarizes the insights gained in automatic term weighting, and provides baseline single term indexing models with which other more elaborate content analysis procedures can be compared.
IEEE Transactions on Information TheoryDivergence measures based on the Shannon entropy
5,027 Citations1991Jinfeng Lin
A novel class of information-theoretic divergence measures based on the Shannon entropy is introduced, which do not require the condition of absolute continuity to be satisfied by the probability distributions involved and are established in terms of bounds.
ACM Transactions on Information SystemsCumulated gain-based evaluation of IR techniques
4,634 Citations2002Kalervo Järvelin, Jaana Kekäläinen
This article proposes several novel measures that compute the cumulative gain the user obtains by examining the retrieval result up to a given ranked position, and test results indicate that the proposed measures credit IR methods for their ability to retrieve highly relevant documents and allow testing of statistical significance of effectiveness differences.
Machine LearningUnsupervised Learning by Probabilistic Latent Semantic Analysis
2,443 Citations2001Thomas Hofmann
This paper proposes to make use of a temperature controlled version of the Expectation Maximization algorithm for model fitting, which has shown excellent performance in practice, and results in a more principled approach with a solid foundation in statistical inference.
Journal of the American Society for Information ScienceRelevance weighting of search terms
2,068 Citations1976Stephen Robertson, Karen Spärck Jones
This paper examines statistical techniques for exploiting relevance information to weight search terms using information about the distribution of index terms in documents in general and shows that specific weighted search methods are implied by a general probabilistic theory of retrieval.
SIAM ReviewUsing Linear Algebra for Intelligent Information Retrieval
1,484 Citations1995Michael W. Berry, Susan Dumais +1 more
A lexical match between words in users’ requests and those in or assigned to documents in a database helps retrieve textual materials from scientific databases.
Journal of the American Society for Information Science and TechnologyCo‐citation analysis, bibliographic coupling, and direct citation: Which citation approach represents the research front most accurately?
1,387 Citations2010Kevin W. Boyack, Richard Klavans
ScientometricsMapping the backbone of science
952 Citations2005Kevin W. Boyack, Richard Klavans +1 more
A new map representing the structure of all of science, based on journal articles, is presented, including both the natural and social sciences, including biochemistry, which appears as the most interdisciplinary discipline in science.
Information Processing & ManagementA probabilistic model of information retrieval: development and comparative experiments
947 Citations2000Karen Spärck Jones, Steve Walker +1 more
Reexamining the cluster hypothesis
828 Citations1996Marti A. Hearst, Jan Pedersen
This work systematically evaluates Scatter/Gather in this context and finds significant improvements over similarity search ranking alone and provides evidence validating the cluster hypothesis which states that relevant documents tend to be more similar to each other than to non-relevant documents.
PLoS BiologyTextpresso: An Ontology-Based Information Retrieval and Extraction System for Biological Literature
662 Citations2004Hans‐Michael Müller, Eimear E. Kenny +1 more
Extraction of particular biological facts can be accelerated significantly by ontologies, with Textpresso automatically performing nearly as well as expert curators to identify sentences; in searches for two uniquely named genes and an interaction term, the ontology confers a 3-fold increase of search efficiency.
Information Storage and RetrievalThe use of hierarchic clustering in information retrieval
522 Citations1971N. Jardine, C. J. van Rijsbergen
It is shown that cluster-based retrieval strategies can be devised which are as effective as linear associative retrieval strategies and much more efficient.
ACM Transactions on Database SystemsIndex-driven similarity search in metric spaces (Survey Article)
437 Citations2003Gı́sli R. Hjaltason, Hanan Samet
This article focuses on methods for similarity search that make the general assumption that similarity is represented with a distance metric d, and presents algorithms for common types of queries that operate on an arbitrary "search hierarchy."
IEEE Transactions on Knowledge and Data EngineeringAn Adaptation of the Vector-Space Model for Ontology-Based Information Retrieval
417 Citations2007Pablo Castells, Miriam Fernández +1 more
A model for the exploitation of ontology-based knowledge bases to improve search over large document repositories and is combined with conventional keyword-based retrieval to achieve tolerance to knowledge base incompleteness.
Information Processing & ManagementImplementing agglomerative hierarchic clustering algorithms for use in document retrieval
323 Citations1986Ellen M. Voorhees
The implementations of three agglomerative hierarchic clustering algorithms that exploit sparsity so that collections much larger than the algorithms'' worst case running times would suggest can be clustered.
Text mining : applications and theory
289 Citations2010Michael W. Berry, Jacob Kogan
This work focuses on text mining and cybercrime, and on the development of nonnegative matrix factorization for email classification problems using NMF-based classification methods.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEOpenOrd: an open-source toolbox for large graph layout
278 Citations2011Shawn Martin, William M. Brown +2 more
An open-source toolbox for drawing large-scale undirected graphs based on a previously implemented closed-source algorithm known as VxOrd, which is extended by incorporating edge-cutting, a multi-level approach, average-link clustering, and a parallel implementation.
Information Processing & ManagementA probabilistic model of information retrieval: development and comparative experiments
272 Citations2000Karen Spärck Jones, Steve Walker +1 more
Information Processing & ManagementCombining the evidence of multiple query representations for information retrieval
268 Citations1995Nicholas J. Belkin, Paul B. Kantor +2 more
Both projects found that the best method of combination often led to results that were better than the best performing single query, and the combined results from the two projects have also been combined by data fusion.
BMC BioinformaticsPubMed related articles: a probabilistic topic-based model for content similarity
249 Citations2007Jimmy Lin, W. John Wilbur
A probabilistic topic-based model for content similarity called pmra that underlies the related article search feature in PubMed, and a novel technique for estimating parameters that does not require human relevance judgments is described.
Journal of the American Society for Information ScienceOn selecting a measure of retrieval effectiveness
229 Citations1973William S. Cooper
Two kinds of solution to the problems of the impracticality of the naive evaluation procedure are taken up, and the first answers the questions in terms of the reasonableness of the simplifying assumptions needed to get from the naive measure to the proposed substitute.
ACM Transactions on Information SystemsA semidiscrete matrix decomposition for latent semantic indexing information retrieval
224 Citations1998Tamara G. Kolda, Dianne P. O’Leary
It is shown that SDD- based LSI does as well as SVD-based LSI in terms of document retrieval while requiring only one-twentieth the storage and one-half the time to compute each query.
Journal of the American Medical Informatics AssociationText Categorization Models for High-Quality Article Retrieval in Internal Medicine
181 Citations2004Yindalon Aphinyanaphongs
Machine learning methods are shown to be possible to automatically build models for retrieving high-quality, content-specific articles using inclusion or citation by the ACP Journal Club as a gold standard in a given time period in internal medicine that perform better than the 1994 PubMed clinical query filters.
Journal of the American Society for Information Science and TechnologyIdentifying a better measure of relatedness for mapping science
160 Citations2005Richard Klavans, Kevin W. Boyack
A new framework for assessing the performance of relatedness measures and visualization algorithms that contains four factors: accuracy, coverage, scalability, and robustness is proposed.
Proceedings of the National Academy of SciencesFrom paragraph to graph: Latent semantic analysis for information visualization
147 Citations2004Thomas K. Landauer, Darrell Laham +1 more
It is suggested that the use of a high dimensional dynamic viewer with an effective projection pursuit routine and user control, coupled with the exquisite abilities of the human visual system, can often succeed in discovering multiple revealing views that are missed by current computational algorithms.
Lecture notes in computer scienceAI 2005: Advances in Artificial Intelligence
123 Citations2005Chengqi Zhang, Ray Jarvis
Journal of the American Society for Information Science and TechnologyProbabilistic topic decomposition of an eighteenth‐century American newspaper
115 Citations2006David Newman, Sharon Block
BioinformaticsText similarity: an alternative way to search MEDLINE
111 Citations2006James A. Lewis, Stephan Ossowski +3 more
A new, hybrid search system for Medline is created that takes natural text as input and then delivers results with high precision and recall, and a fast, low-sensitivity weighted keyword-based first pass algorithm was developed that is sensitive, fast and easy to use.
Journal of InformetricsDocument–document similarity approaches and science mapping: Experimental comparison of five approaches
91 Citations2009Per Ahlgren, Cristian Colliander
It is shown that it is possible to achieve a very good approximation of the classification by means of automatic grouping of articles, and how well the approaches agree with a ground truth subject classification of the test documents is investigated.
Journal of InformetricsVisual conceptualizations and models of science
78 Citations2009Katy Börner, Andrea Scharnhorst
This Journal of Informetrics special issue aims to improve the understanding of the structure and dynamics of science by reviewing and advancing existing conceptualizations and models of scholarly activity by discussing challenges towards a theoretically grounded and practically useful science of science.
BMC BioinformaticsMScanner: a classifier for retrieving Medline citations
65 Citations2008Graham Poulter, Daniel L. Rubin +2 more
MScanner is an effective non-domain-specific classifier that operates on the entire Medline database, and is suited to retrieving topics for which many features may indicate relevance.
ScientometricsBibliographic coupling, common abstract stems and clustering: A comparison of two document-document similarity approaches in the context of science mapping
49 Citations2008Per Ahlgren, Bo Jarneving
The expert classification indicates that the field of information retrieval, as represented by one volume of articles published in Information Retrieval, is fairly heterogeneous regarding research themes, since the classification is associated with 15 themes.
Journal of Biomedical InformaticsBiomedical knowledge navigation by literature clustering
48 Citations2006Yasunori Yamamoto, Toshihisa Takagi
Journal of the American Society for Information Science and TechnologyLink‐based similarity measures for the classification of Web documents
46 Citations2005Pável Calado, Marco Cristo +4 more
The authors evaluate how the link structure of the Web can be used to determine a measure of similarity appropriate for document classification, finding that link information alone allows classifying documents with an average precision of 86p and when combined with a traditional text-based classifier, precision increases to values of up to 90p.
A comparative study of citations and links in document classification
46 Citations2006Thierson Couto, Marco Cristo +5 more
A comparative study of digital library citations and Web links, in the context of automatic text classification, shows that there are in fact differences between citations and links in this context and proposes a simple and effective way of combining a traditional text based classifier with a citation-link based classifiers.
BMC GenomicsSemantically linking and browsing PubMed abstracts with gene ontology
40 Citations2008Bhanu C Vanteru, Jahangheer Shaik +1 more
The analysis suggests that the SEGOPubmed performs better than the classic GOPubmed as it incorporates semantics, and the proposed semantic-sensitive technique outperformed the string comparison based techniques in associating the relevant abstracts to the GO terms.
BioinformaticsPuReD-MCL: a graph-based PubMed document clustering methodology
40 Citations2008Θεοδόσιος Θεοδοσίου, Nikos Darzentas +2 more
PuReD-MCL successfully reproduces the annotated results obtained from TextQuest, while at the same time provides additional insights into the clusters and the corresponding documents, which are based on the graph clustering algorithm MCL and relevant resources from PubMed.
Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries
36 Citations2016
This year's technical program will feature 27 research papers, to be presented in 7 sessions, with topics ranging from Wikipedia and Newspaper Analysis to Curation and Education to Recommendation and Prediction, and the nominees for the best paper awards.
Generalized hebbian algorithm for incremental latent semantic analysis
34 Citations2005Genevieve Gorrell, Brandyn J. Webb
The Generalized Hebbian Algorithm is shown to be equivalent to Latent Semantic Analysis, and applicable to a range of LSAstyle tasks, and allows very large datasets to be processed.
Lecture notes in computer scienceCombining Contents and Citations for Scientific Document Classification
28 Citations2005Minh Duc Cao, Xiaoying Gao
A classification system that exploits the content information as well as citation structure for scientific paper classification, and shows that, combining contents and citations significantly improves the system performance.
HAL (Le Centre pour la Communication Scientifique Directe)Feature-based cluster validation for high-dimensional data
20 Citations2008Randa Kassab, Jean-Charles Lamirel
A feature-based cluster validation criterion which can prune out unreliable clusters which have no correlated features and thus no specific description of their content is introduced.
Lirias (KU Leuven)Integration of textual content and link information for accurate clustering of science fields
17 Citations2006Frizo Janssens, Viet Tran Quoc +2 more
Content‐Based Spam Email Classification using Machine‐Learning Algorithms
5 Citations2010Eric P. Jiang