[Sigmetrics] Topic modelling in arts and humanities research

[Loet Leydesdorff]

Dear Jonathan,

I read the report with interest. We previously had some validity issues 
with topic modeling (Leydesdorff & Nerghes, 2017), which we discussed 
before. Have these issues been solved by moving from LDA to Non-negative 
Matrix Factorization as a method?

You claim (p. 15) that the results are "meaningful," but elsewhere you 
formulate more cauteously that "topic modeling is a promising approach 
that can capture trends in research production."
"Can" or "may"?

Are the data (and perhaps some results) available online? Tobias Hecking 
(Duisburg) and I are trying to upscale the previous study and would love 
to use them as an example.

Best,
Loet

Reference:
Leydesdorff, L., & Nerghes, A. (2017). Co-word maps and topic modeling: 
A comparison using small and medium-sized corpora (N < 1,000). 
[Article]. Journal of the Association for Information Science and 
Technology, 68(4), 1024-1035. doi: 10.1002/asi.23740

--------------------------------------------------------------------------------
Loet Leydesdorff

Professor emeritus, University of Amsterdam
Amsterdam School of Communication Research (ASCoR)

loet at leydesdorff.net <mailto:loet at leydesdorff.net>; 
http://www.leydesdorff.net/
Associate Faculty, SPRU, <http://www.sussex.ac.uk/spru/>University of 
Sussex;

Guest Professor Zhejiang Univ. <http://www.zju.edu.cn/english/>, 
Hangzhou; Visiting Professor, ISTIC, 
<http://www.istic.ac.cn/Eng/brief_en.html>Beijing;

Visiting Fellow, Birkbeck <http://www.bbk.ac.uk/>, University of London;

http://scholar.google.com/citations?user=ych9gNYAAAAJ&hl=en


------ Original Message ------
From: "Jonathan Adams" <j.adams at digital-science.com>
To: "SIGMETRICS (sigmetrics at mail.asis.org)" <SIGMETRICS at mail.asis.org>
Sent: 11/24/2017 11:56:35 AM
Subject: [Sigmetrics] Topic modelling in arts and humanities research

>Dear Colleagues
>
>Digital Science’s latest report analyses arts and humanities research 
>through  topic modelling of grant applications, unveiling an innovative 
>and richer understanding of the research activity in disciplines that 
>have received much less attention than STEM research.
>
>Today, working with the Arts and Humanities Research Council 
><http://www.ahrc.ac.uk/> (AHRC), we have released our latest Digital 
>Research Report on: “Topic Modelling of Research in the Arts and 
>Humanities <https://doi.org/10.6084/m9.figshare.5621260.v1>.” The 
>report is an analysis of AHRC grant applications and details new topic 
>modelling applications for analysing research funding data. This is the 
>first time these methods have been applied to a national funding 
>dataset of research grants  and one of the first comprehensive 
>analytical views across research in the arts and humanities.
>
>--
>Dr Jonathan Adams
>Chief Scientist, Digital Science
>Visiting Professor, King's College London
>https://www.kcl.ac.uk/sspp/policy-institute/Visiting-professors-fellows/adams.aspx
>
>M/ +44 7964 908449
>E/ j.adams at digital-science.com
>
>
>
>Custom reporting and analysis to help you make better decisions faster
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.asis.org/pipermail/sigmetrics/attachments/20171126/52899739/attachment.html>