There is some work comparing topic modeling to qualitative analysis. Here
are two papers I'd suggest:
Baumer, Eric P. S., David Mimno, Shion Guha, Emily Quan, and Geri K. Gay.
“Comparing Grounded Theory and Topic Modeling: Extreme Divergence or
Unlikely Convergence?” Journal of the Association for Information Science
and Technology 68, no. 6 (2017): 1397–1410.
https://doi.org/10.1002/asi.23786
Roberts, Margaret E., Brandon M. Stewart, Dustin Tingley, Christopher
Lucas, Jetson Leder-Luis, Shana Kushner Gadarian, Bethany Albertson, and
David G. Rand. “Structural Topic Models for Open-Ended Survey Responses.”
American Journal of Political Science 58, no. 4 (2014): 1064–82.
https://doi.org/10.1111/ajps.12103
I'd welcome others!
-Jodi
On Mon, Sep 12, 2022 at 9:40 AM Eric Lease Morgan <[log in to unmask]> wrote:
> On Sep 9, 2022, at 11:25 AM, Kimberli Kelmor <
> [log in to unmask]> wrote:
>
> > A while back we kind of talked around qualitative analysis tools. I'd
> like to query the group about it directly, though.
> >
> > What do people use for qualitative data analysis and storage? I've used
> NVivo before and liked it, but it is pricey and maybe both under and
> overkill. What else is out there?
> >
> > A related question, is there an open data platform that is geared toward
> qualitative data instead of quantitative data? I'm looking to find
> something already available that has a strong data/document repository
> layer, a strong analysis layer, and a strong and flexible presentation or
> publishing layer.
> >
> > Many thanks for any information you can share!
> >
> > --
> > Kimberli M. Kelmor
>
>
> Please correct me if I'm wrong. In this case, "qualitative analysis tools"
> are applications where one: 1) assembles a corpus of one or more documents,
> 2) articulates a vocabulary of topics or themes, 3) peruses ("reads") items
> in the corpus assigning vocabulary terms to parts or the whole of the
> items, and 4) does statistical analysis against the assignments. In the end
> the student, researcher, or scholar will address questions such as "How did
> a given idea ebb and flow over time?", "To what degree do these sets of
> people express a given thing?", or "How often was such and such mentioned?"
> Correct?
>
> If this be the case, then I believe the same research questions can be
> addressed more consistently and at a larger scale if natural langauge
> processing (NLP) methods were applied to the corpus. At the same time, the
> application of NLP ought not be considered a replacement for qualitative
> analsysis tools nor tradidtional reading. Instead, the application of NLP
> ought to be considered a supplemental method of analysis.
>
> --
> Eric Morgan
> Navari Family Center for Digital Scholarship
> University of Notre Dame
>
|