SPSS Text Analysis 2.0

classic Classic list List threaded Threaded
3 messages Options
Reply | Threaded
Open this post in threaded view
|

SPSS Text Analysis 2.0

Björn Türoque
Does anyone know where to get additional libraries for SPSS Text Analysis 2
specifically I am looking for libraries that will help with the
classification of people into different SOC occupation categories. I know it
is possible to make these using the SPSS text analysis tool, but I am hoping
that someone on this list will know where a copy of  various pre-programmed
and tested dictionaries can be acquired.

Don
Reply | Threaded
Open this post in threaded view
|

Re: SPSS Text Analysis 2.0

Björn Türoque
I only have limited experience with NVIVO, but in comparisson to SPSS Text
Analysis 2.0, NVIVO is a little easier to use and a bit more intuitive when
analysing the results. The benefit of using SPSS Text Analysis 2.0 is that
it is very good at translating qualitiative data into quantitative data and
re-incorporating it back into your origional dataset for analysis.

I would like to use Text Analysis to categorize a persons written in
occupation into a specific SOC code, something that would normally take a
coder a few hours to get down, and has the possibility of human error. I
know it is possible to program libraries/dictionaries into SPSS 2.0 so that
the computer will do most of the coding for you, but I was just hoping that
someone would have knowledge of where to get
pre-programmed libraries/dictionaries.

The availablity of pre-programmed dictionaries for NVIVO is a HUGE plus for
using that program, they are easy to come by on the net. I know it is
possible to import dictionaries to SPSS Text Analysis, but it is impossible
to find the SPSS dictionaries to import. SPSS might want to think about
allowing users to incorporate libraries/dictionaries from some other
programs such as NVIVO and other qualitative analysis tools.

Again if anyone has suggestions, please let me know.


Don


On 2/28/07, Gonzales, Dana L <[hidden email]> wrote:

>
> You mean your institution can actually afford the license? LOL! Can you
> tell
> me if this is better than Nvivo, N6 or Atlasti? I don't know anyone who
> actually uses SPSS Text Analysis.
>
> Thanks,
>
> Dana
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
> Don
> Asay
> Sent: Wednesday, February 28, 2007 2:49 PM
> To: [hidden email]
> Subject: SPSS Text Analysis 2.0
>
> Does anyone know where to get additional libraries for SPSS Text Analysis
> 2
> specifically I am looking for libraries that will help with the
> classification of people into different SOC occupation categories. I know
> it
> is possible to make these using the SPSS text analysis tool, but I am
> hoping
> that someone on this list will know where a copy of  various
> pre-programmed
> and tested dictionaries can be acquired.
>
> Don
>
> Confidentiality Notice: This e-mail message, including any attachments, is
> for the sole use of the intended recipient(s) and may contain confidential
> and privileged information.  Any unauthorized review, use, disclosure or
> distribution is prohibited.  If you are not the intended recipient, please
> contact the sender by reply e-mail and destroy all copies of the original
> message.
>
>
Reply | Threaded
Open this post in threaded view
|

Re: SPSS Text Analysis 2.0

Muenchen, Robert A (Bob)
I have very limited experience with NVIVO too, but I'm under the
impression that it does not use dictionaries. If you go to
http://www.qsrinternational.com and search their support forum and FAQ
file for "dictionary" you get no hits, but they may call them something
else. Can you point out a site that makes them available? I thought that
NVIVO was a manual program which helps *you* decide how to categorize
each bit of text you read.

SPSS Text Analysis for Surveys uses its linguistic programming &
dictionaries to categorize the text for you. It will go through
thousands of paragraphs quickly, something that would take you a long
time to code using most qualitative packages. My favorite example of
using it was when I was making up all kinds of product comments just to
see how good it was. I entered, "This product rocks my world" just for
fun & was stunned to see it recognize that as a positive endorsement! It
has extensive dictionaries of such positive and negative comments.

The state of text analysis today is rather frustrating. Most vendors
prefer only a single method of analysis. SPSS likes linguistics, SAS
uses latent semantic analysis & clustering, WordStat uses a straight
dictionary (your own or standard one such as those at
http://www.provalisresearch.com/wordstat/LIWC.html ) approach with
statistical analysis, Atlas/Nvivo/QDA Miner use a manual approach and so
forth. Eventually we'll see these approaches in one product. The closest
step toward that goal is the combination of QDA Miner and WordStat. Both
from Provalis Research, they allow you to use blend manual and automated
approaches in a wide range of combinations. Quite affordable too,
especially academic site licenses.

Cheers,
Bob

=========================================================
Bob Muenchen (pronounced Min'-chen), Manager
Statistical Consulting Center
U of TN Office of Information Technology
200 Stokely Management Center, Knoxville, TN 37996-0520
Voice: (865) 974-5230
FAX: (865) 974-4810
Email: [hidden email]
Web: http://oit.utk.edu/scc,
News: http://listserv.utk.edu/archives/statnews.html
=========================================================


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Don Asay
Sent: Thursday, March 01, 2007 12:35 PM
To: [hidden email]
Subject: Re: SPSS Text Analysis 2.0

I only have limited experience with NVIVO, but in comparisson to SPSS
Text
Analysis 2.0, NVIVO is a little easier to use and a bit more intuitive
when
analysing the results. The benefit of using SPSS Text Analysis 2.0 is
that
it is very good at translating qualitiative data into quantitative data
and
re-incorporating it back into your origional dataset for analysis.

I would like to use Text Analysis to categorize a persons written in
occupation into a specific SOC code, something that would normally take
a
coder a few hours to get down, and has the possibility of human error. I
know it is possible to program libraries/dictionaries into SPSS 2.0 so
that
the computer will do most of the coding for you, but I was just hoping
that
someone would have knowledge of where to get
pre-programmed libraries/dictionaries.

The availablity of pre-programmed dictionaries for NVIVO is a HUGE plus
for
using that program, they are easy to come by on the net. I know it is
possible to import dictionaries to SPSS Text Analysis, but it is
impossible
to find the SPSS dictionaries to import. SPSS might want to think about
allowing users to incorporate libraries/dictionaries from some other
programs such as NVIVO and other qualitative analysis tools.

Again if anyone has suggestions, please let me know.


Don


On 2/28/07, Gonzales, Dana L <[hidden email]> wrote:
>
> You mean your institution can actually afford the license? LOL! Can
you
> tell
> me if this is better than Nvivo, N6 or Atlasti? I don't know anyone
who
> actually uses SPSS Text Analysis.
>
> Thanks,
>
> Dana
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf
Of
> Don
> Asay
> Sent: Wednesday, February 28, 2007 2:49 PM
> To: [hidden email]
> Subject: SPSS Text Analysis 2.0
>
> Does anyone know where to get additional libraries for SPSS Text
Analysis
> 2
> specifically I am looking for libraries that will help with the
> classification of people into different SOC occupation categories. I
know

> it
> is possible to make these using the SPSS text analysis tool, but I am
> hoping
> that someone on this list will know where a copy of  various
> pre-programmed
> and tested dictionaries can be acquired.
>
> Don
>
> Confidentiality Notice: This e-mail message, including any
attachments, is
> for the sole use of the intended recipient(s) and may contain
confidential
> and privileged information.  Any unauthorized review, use, disclosure
or
> distribution is prohibited.  If you are not the intended recipient,
please
> contact the sender by reply e-mail and destroy all copies of the
original
> message.
>
>