You are viewing a plain text version of this content. The canonical link for it is here.
Posted to users@opennlp.apache.org by Madhav Sharan <ms...@usc.edu> on 2017/04/09 08:15:33 UTC

LIWC or other psychological text analysis features

Hi OpenNLP users -

Can someone tell me if there is any Feature Extractor in OpenNLP for LIWC
or other psychological text analysis features?

If there is not is then is there any community interest in building one? I
could only find paid versions of LIWC so probably so we might need to look
for alternate sources. It will be great if someone can share their
experiences extracting any such kind of features.

http://liwc.wpengine.com/how-it-works/

--
Madhav Sharan

Re: LIWC or other psychological text analysis features

Posted by Madhav Sharan <ms...@usc.edu>.
Thanks for showing interest. I tried to find a free version of LIWC but
could not find one.

As I was looking for more such features I came across psychological
features created by Asitang and used in Memex for persona linking [0]. I
think these are great and proved to be useful and OpenNLP is a very good
place to have these. These are already in tika-python and used in other
memex projects.

I am creating a JIRA in OpenNLP and I'll be working on adding these
features.

If anyone has more ideas please feel free to tell us here and we can add
them to list. I also have another list with similar features [1].

[0] Features used in other Memex Project -
https://github.com/chrismattmann/tika-similarity#similarity-based-on-stylisticauthorship-features


[1] My own thoughts while taking NLP and other human communication class at
USC - https://github.com/smadha/text-to-vector/wiki

--
Madhav Sharan


On Sun, Apr 9, 2017 at 3:44 PM, William Colen <wi...@gmail.com>
wrote:

> +1
>
> 2017-04-09 17:44 GMT-03:00 Suneel Marthi <sm...@apache.org>:
>
> > +1 to include this
> >
> > On Sun, Apr 9, 2017 at 4:38 PM, Mattmann, Chris A (3010) <
> > chris.a.mattmann@jpl.nasa.gov> wrote:
> >
> > > FYI this is related to another feature extraction that we are doing in
> my
> > > USC group (like the
> > > Sentiment Analyzer) related to Age detection.
> > >
> > > Our early work is here: https://urldefense.proofpoint.
> com/v2/url?u=https-3A__github.com_USCDataScience_AgePredictor&d=DwIBaQ&c=
> clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=DhBa2eLkbd4gAFB01lkNgg&m=
> KDNFU3_06XWawuXppD71yDO30uADh8mGpq5nlRrD1SE&s=a4Shj_
> esT1ktFPhjXAaUln1pNWiTMBPGx4cPA9bkCNg&e=
> > > Paper describing work is here: https://urldefense.proofpoint.
> com/v2/url?u=https-3A__arxiv.org_abs_1610.00852&d=DwIBaQ&c=
> clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=DhBa2eLkbd4gAFB01lkNgg&m=
> KDNFU3_06XWawuXppD71yDO30uADh8mGpq5nlRrD1SE&s=Rp8q7H-IQ8kF6H_
> e2g1ZQ_5kHNMU1CFrAPZM5qCBB-M&e=
> > >
> > >
> > > ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> > ++++++++++++++
> > > Chris Mattmann, Ph.D.
> > > Principal Data Scientist, Engineering Administrative Office (3010)
> > > Manager, NSF & Open Source Projects Formulation and Development Offices
> > > (8212)
> > > NASA Jet Propulsion Laboratory Pasadena, CA 91109 USA
> > > Office: 180-503E, Mailstop: 180-503
> > > Email: chris.a.mattmann@nasa.gov
> > > WWW:  http://sunset.usc.edu/~mattmann/
> > > ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> > ++++++++++++++
> > > Director, Information Retrieval and Data Science Group (IRDS)
> > > Adjunct Associate Professor, Computer Science Department
> > > University of Southern California, Los Angeles, CA 90089 USA
> > > WWW: http://irds.usc.edu/
> > > ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> > ++++++++++++++
> > >
> > >
> > > From: Madhav Sharan <ms...@usc.edu>
> > > Date: Sunday, April 9, 2017 at 1:15 AM
> > > To: "users@opennlp.apache.org" <us...@opennlp.apache.org>
> > > Cc: "Mattmann, Chris A (3010)" <ch...@jpl.nasa.gov>
> > > Subject: LIWC or other psychological text analysis features
> > >
> > > Hi OpenNLP users -
> > >
> > > Can someone tell me if there is any Feature Extractor in OpenNLP for
> LIWC
> > > or other psychological text analysis features?
> > >
> > > If there is not is then is there any community interest in building
> one?
> > I
> > > could only find paid versions of LIWC so probably so we might need to
> > look
> > > for alternate sources. It will be great if someone can share their
> > > experiences extracting any such kind of features.
> > >
> > > https://urldefense.proofpoint.com/v2/url?u=http-3A__liwc.
> wpengine.com_how-2Dit-2Dworks_&d=DwIBaQ&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN
> 0H8p7CSfnc_gI&r=DhBa2eLkbd4gAFB01lkNgg&m=KDNFU3_
> 06XWawuXppD71yDO30uADh8mGpq5nlRrD1SE&s=oZUHCIHW0b3U-
> fOx8p2oWYnsKOhUmOdLmnVVQm-06zU&e=
> > >
> > > --
> > > Madhav Sharan
> > >
> > >
> >
>

Re: LIWC or other psychological text analysis features

Posted by William Colen <wi...@gmail.com>.
+1

2017-04-09 17:44 GMT-03:00 Suneel Marthi <sm...@apache.org>:

> +1 to include this
>
> On Sun, Apr 9, 2017 at 4:38 PM, Mattmann, Chris A (3010) <
> chris.a.mattmann@jpl.nasa.gov> wrote:
>
> > FYI this is related to another feature extraction that we are doing in my
> > USC group (like the
> > Sentiment Analyzer) related to Age detection.
> >
> > Our early work is here: https://github.com/USCDataScience/AgePredictor
> > Paper describing work is here: https://arxiv.org/abs/1610.00852
> >
> >
> > ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> ++++++++++++++
> > Chris Mattmann, Ph.D.
> > Principal Data Scientist, Engineering Administrative Office (3010)
> > Manager, NSF & Open Source Projects Formulation and Development Offices
> > (8212)
> > NASA Jet Propulsion Laboratory Pasadena, CA 91109 USA
> > Office: 180-503E, Mailstop: 180-503
> > Email: chris.a.mattmann@nasa.gov
> > WWW:  http://sunset.usc.edu/~mattmann/
> > ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> ++++++++++++++
> > Director, Information Retrieval and Data Science Group (IRDS)
> > Adjunct Associate Professor, Computer Science Department
> > University of Southern California, Los Angeles, CA 90089 USA
> > WWW: http://irds.usc.edu/
> > ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> ++++++++++++++
> >
> >
> > From: Madhav Sharan <ms...@usc.edu>
> > Date: Sunday, April 9, 2017 at 1:15 AM
> > To: "users@opennlp.apache.org" <us...@opennlp.apache.org>
> > Cc: "Mattmann, Chris A (3010)" <ch...@jpl.nasa.gov>
> > Subject: LIWC or other psychological text analysis features
> >
> > Hi OpenNLP users -
> >
> > Can someone tell me if there is any Feature Extractor in OpenNLP for LIWC
> > or other psychological text analysis features?
> >
> > If there is not is then is there any community interest in building one?
> I
> > could only find paid versions of LIWC so probably so we might need to
> look
> > for alternate sources. It will be great if someone can share their
> > experiences extracting any such kind of features.
> >
> > http://liwc.wpengine.com/how-it-works/
> >
> > --
> > Madhav Sharan
> >
> >
>

Re: LIWC or other psychological text analysis features

Posted by Suneel Marthi <sm...@apache.org>.
+1 to include this

On Sun, Apr 9, 2017 at 4:38 PM, Mattmann, Chris A (3010) <
chris.a.mattmann@jpl.nasa.gov> wrote:

> FYI this is related to another feature extraction that we are doing in my
> USC group (like the
> Sentiment Analyzer) related to Age detection.
>
> Our early work is here: https://github.com/USCDataScience/AgePredictor
> Paper describing work is here: https://arxiv.org/abs/1610.00852
>
>
> ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> Chris Mattmann, Ph.D.
> Principal Data Scientist, Engineering Administrative Office (3010)
> Manager, NSF & Open Source Projects Formulation and Development Offices
> (8212)
> NASA Jet Propulsion Laboratory Pasadena, CA 91109 USA
> Office: 180-503E, Mailstop: 180-503
> Email: chris.a.mattmann@nasa.gov
> WWW:  http://sunset.usc.edu/~mattmann/
> ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
> Director, Information Retrieval and Data Science Group (IRDS)
> Adjunct Associate Professor, Computer Science Department
> University of Southern California, Los Angeles, CA 90089 USA
> WWW: http://irds.usc.edu/
> ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>
>
> From: Madhav Sharan <ms...@usc.edu>
> Date: Sunday, April 9, 2017 at 1:15 AM
> To: "users@opennlp.apache.org" <us...@opennlp.apache.org>
> Cc: "Mattmann, Chris A (3010)" <ch...@jpl.nasa.gov>
> Subject: LIWC or other psychological text analysis features
>
> Hi OpenNLP users -
>
> Can someone tell me if there is any Feature Extractor in OpenNLP for LIWC
> or other psychological text analysis features?
>
> If there is not is then is there any community interest in building one? I
> could only find paid versions of LIWC so probably so we might need to look
> for alternate sources. It will be great if someone can share their
> experiences extracting any such kind of features.
>
> http://liwc.wpengine.com/how-it-works/
>
> --
> Madhav Sharan
>
>

Re: LIWC or other psychological text analysis features

Posted by "Mattmann, Chris A (3010)" <ch...@jpl.nasa.gov>.
FYI this is related to another feature extraction that we are doing in my USC group (like the
Sentiment Analyzer) related to Age detection.

Our early work is here: https://github.com/USCDataScience/AgePredictor
Paper describing work is here: https://arxiv.org/abs/1610.00852


++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Chris Mattmann, Ph.D.
Principal Data Scientist, Engineering Administrative Office (3010)
Manager, NSF & Open Source Projects Formulation and Development Offices (8212)
NASA Jet Propulsion Laboratory Pasadena, CA 91109 USA
Office: 180-503E, Mailstop: 180-503
Email: chris.a.mattmann@nasa.gov
WWW:  http://sunset.usc.edu/~mattmann/
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Director, Information Retrieval and Data Science Group (IRDS)
Adjunct Associate Professor, Computer Science Department
University of Southern California, Los Angeles, CA 90089 USA
WWW: http://irds.usc.edu/
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++


From: Madhav Sharan <ms...@usc.edu>
Date: Sunday, April 9, 2017 at 1:15 AM
To: "users@opennlp.apache.org" <us...@opennlp.apache.org>
Cc: "Mattmann, Chris A (3010)" <ch...@jpl.nasa.gov>
Subject: LIWC or other psychological text analysis features

Hi OpenNLP users -

Can someone tell me if there is any Feature Extractor in OpenNLP for LIWC or other psychological text analysis features?

If there is not is then is there any community interest in building one? I could only find paid versions of LIWC so probably so we might need to look for alternate sources. It will be great if someone can share their experiences extracting any such kind of features.

http://liwc.wpengine.com/how-it-works/

--
Madhav Sharan