[Sigmetrics] Topic extraction challenge

Andrea Scharnhorst andrea.scharnhorst at dans.knaw.nl
Tue Mar 14 14:54:19 EDT 2017

Preprints of most of the articles can be found at
http://www.topic-challenge.info/ -> publications. We work on getting the pending one of Koopman et al on-line!
Good point, thanks for your interest

From: Andreas Strotmann
Date: Tuesday 14 March 2017 at 19:04
To: Andrea Scharnhorst
Cc: "sigmetrics at mail.asis.org<mailto:sigmetrics at mail.asis.org>"
Subject: Re: [Sigmetrics] Topic extraction challenge

Actually, this would be much more useful if we had the full text of these articles, too.  There is a lot of research going on with respect to in-text citation/citation context analysis these days.  That research would benefit greatly from such an opportunity for comparisons (as would be the efforts to improve existing citation databases, I suspect.)

On Tue, Mar 14, 2017 at 8:35 AM, Andrea Scharnhorst <andrea.scharnhorst at dans.knaw.nl<mailto:andrea.scharnhorst at dans.knaw.nl>> wrote:
Please take apologies for cross-posting

Dear colleagues,

You might be interested to learn that Clarivate Analytics has agreed to make available a Web of Science data set (111,616 articles in Astrophysics and Astronomy, "Astro Data Set") which allows us to invite everybody interested to participate in a topic extraction challenge so we can collectively study and learn from the systematic comparison of topic extraction approaches. For details about the challenge and how to access the data see: www.topic-challenge.info<http://www.topic-challenge.info>.

The activity of exploring differences between topic extraction approaches originated from discussions at the annual advisory board meeting of a project on measuring the epistemic diversity of research by Frank Havemann, Michael Heinz and Jochen Gläser in Berlin, Germany, and is documented in a special issue "Same Data, Different Results?" of the journal Scientometrics (see list of forthcoming articles below).

We would like to invite you and your colleagues to participate in the topic extraction challenge, and would appreciate your support in  spreading the news. A first opportunity to discuss new topic extraction solutions and the challenge of comparing approaches will be provided this October at a special session at the 2017 ISSI conference in Wuhan, China (http://www.issi2017.org). Submission deadline for research in progress papers is April 10. You are welcome to forward this invitation to others who may have an interest in topic extraction from the Astro Data Set. Please send questions to theresa.velden at gmail.com<mailto:theresa.velden at gmail.com>.

With kind regards,

Theresa Velden
(& the other "challengers": Kevin Boyack, Wolfgang Glänzel, Jochen Gläser, Frank Havemann, Andrea Scharnhorst, Bart Thijs, Nees Jan van Eck, Ludo Waltman)

List of forthcoming Scientometrics articles on topic extraction from the Astro Data Set:

Gläser J, Scharnhorst A & Glänzel, W (eds). Introduction: Same data – different results? Towards a comparative approach to the identification of thematic structures in science. DOI: 10.1007/s11192-017-2296-z

Boyack K. Investigating the Effect of Global Data on Topic Detection. DOI: 10.1007/s11192-017-2297-y

Wang, S. & Koopman, R. Clustering articles based on semantic similarity. DOI:10.1007/s11192-017-2298-x

Velden T, Yan S & Lagoze C. Mapping the Cognitive Structure of Astrophysics by Infomap Clustering of the Citation Network and Topic Affinity Analysis. DOI: 10.1007/s11192-017-2299-9

Van Eck, NJ & Waltman, L. Citation-Based Clustering of Publications Using CitNetExplorer and VOSviewer  DOI: 10.1007/s11192-017-2300-7

Glänzel, W & Thijs B. Using Hybrid Methods and `Core Documents' for the Representation of Clusters and Topics. The Astronomy Dataset DOI: 10.1007/s11192-017-2301-6

Havemann F, Gläser J & Heinz M. Memetic Search for Overlapping Topics Based on a Local Evaluation of Link Communities DOI: 10.1007/s11192-017-2302-5

Koopman R, Wang S & Scharnhorst A. Contextualization of Topics: Browsing through the Universe of Bibliographic Information  DOI: 10.1007/s11192-017-2303-4

Boyack, K. Thesaurus-Based Methods for Mapping Contents of Publication Sets  DOI: 10.1007/s11192-017-2304-3

Koopman R & Wang S. Mutual Information Based Labelling and Comparing Clusters  DOI: 10.1007/s11192-017-2305-2

Velden T, Boyack K, Glaser J, Koopman R, Scharnhorst A & Wang S. Comparison of Topic Extraction Approaches and Their Results DOI: 10.1007/s11192-017-2299-9 DOI: 10.1007/s11192-017-2306-1

Theresa Velden, PhD
IPODI/Marie Curie Fellow
Zentrum für Technik und Gesellschaft
Technische Universität Berlin

velden at ztg.tu-berlin.de<mailto:velden at ztg.tu-berlin.de>| tav6 at cornell.edu<mailto:tav6 at cornell.edu> | theresa.velden at gmail.com<mailto:theresa.velden at gmail.com>

SIGMETRICS mailing list
SIGMETRICS at mail.asis.org<mailto:SIGMETRICS at mail.asis.org>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.asis.org/pipermail/sigmetrics/attachments/20170314/cb95b345/attachment.html>

More information about the SIGMETRICS mailing list