Analyses of Topics Maps derived from Neuroanatomical publications
-
1
University of Southern California, Information Sciences Institute, United States
-
2
Indiana University, School of Library and Information Science, United States
Using Latent Dirichlet Allocation (LDA) (Steyvers and Griffiths, 2007) we derived the topical composition of large corpora of full-text neuroanatomical articles that we extracted from PDF documents. Based on the derived topic mixture of each document, we analzed the relationships between documents in a given corpus. We applied Distrivuted Recursive Layout (DrL) (Martin et al., 2011), a graph layout algorithm, to visualize these inter-document relationships. Finally, we replicated this process focusing on different sections of an article (e.g., Abstracts, Methods and Materials) and looked for correspondences between the topics derived from the different sections.
Our poster presents the results of our analyses and describes the details of our methodology. We discus the challenges we faced and how we overcome them. Our ultimate goal is to streamline this procedure and incorporate it into our literature management application to enable other investigators to explore text collections of interest.
We conducted these analyses with articles from two journals: The Journal of Comparative Neurology and Brain Research.
Acknowledgements
This work was supported by the BioScholar (GM083871) and the NeuARt (MH079068) projects. This work was also supported in through the Biomedical Informatics Research Network (1 U24 RR025736-01, NCRR).
References
Steyvers, M., & Griffiths, T. (2007). Probabilistic topic models. Handbook of latent semantic analysis, 427(7), 424–440.
Martin, S., Brown, W. M., Klavans, R., & Boyack, K. W. (2011). OpenOrd: an open-source toolbox for large graph layout. In P. C. Wong, J. Park, M. C. Hao, C. Chen, K. Börner, D. L. Kao, & J. C. Roberts (Eds.), Conference on Visualization and Data Analysis. doi:10.1117/12.8714
Keywords:
Topic maps,
topic models,
Journal of Comparative Neurology,
brain research,
Distributed Recursive Layout,
Latent Dirichlet Allocation
Conference:
Neuroinformatics 2013, Stockholm, Sweden, 27 Aug - 29 Aug, 2013.
Presentation Type:
Poster
Topic:
General neuroinformatics
Citation:
Tallis
M,
Kong
C,
Borner
K and
Burns
GA
(2013). Analyses of Topics Maps derived from Neuroanatomical publications.
Front. Neuroinform.
Conference Abstract:
Neuroinformatics 2013.
doi: 10.3389/conf.fninf.2013.09.00056
Copyright:
The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers.
They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.
The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.
Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.
For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.
Received:
29 Apr 2013;
Published Online:
11 Jul 2013.
*
Correspondence:
Dr. Gully A Burns, University of Southern California, Information Sciences Institute, Marina del Rey, California, 90292, United States, gully@usc.edu