Eric,
You might be interested in something I ran across recently. Aditya
Parameswaran (http://data-people.cs.illinois.edu/) gave a talk at our
campus recently about the efforts of a group he participates in that is
aimed at "simplifying and improving data analytics, i.e., helping users
make better use of their data". He wrote a recent blog post for
O'Reilly on "Enabling Data Science for the Majority"
(https://www.oreilly.com/ideas/enabling-data-science-for-the-majority),
which was the topic of the talk I heard.
He introduced 3 of the 6 projects his team has been working on:
DataSpread, Zenvisage, and OrpheusDB all aimed at what they call "HILDA"
-- "human-in-the-loop data analytics". The 3 projects listed have homes
in github and are linked to from Aditya's page: "Quick Project Links".
At the talk, he said they have hosted versions running and they are
looking for beta testers. There is a live demo of DataSpread at
http://kite.cs.illinois.edu:8080/.
Chris
On 2017-11-09 01:13 PM, Eric Lease Morgan wrote:
I’m thinking about a hands-on workshop on natural language processing & text
mining, below, and your feedback is desired. —ELM
Natural language processing & text mining using freely available tools: "No
programming necessary"
This text outlines a hands-on natural language & text mining workshop.
It is possible to do simple & rudimentary natural language processing & text mining
with a set of freely available tools. No programming is necessary. This workshop
facilitates hands-on exercises demonstrating how this can be done. By participating in this
workshop, students & researchers will be able to:
* identify patterns, anomalies, and trends in their texts
* practice both "distant" and "scalable" reading
* enhance & complement their ability to do "close" reading
* use & understand a corpus of poetry or prose at scale
Activities in the workshop include:
* learning what natural language processing is, and why you should care
* articulating a research question
* creating a corpus
* creating a plain text version of a corpus with Tika [1]
* using Voyant Tools to do some "distant" reading" [2]
* using a concordance (AntConc) to facilitate searching keywords in context
[3]
* creating a simple word list with a text editor
* cleaning & analyzing word lists with OpenRefine [4]
* charting & graphing word lists with Tableau Public [5]
* increasing meaning by extracting parts-of-speech with the Standford POS
Tagger [6]
* increasing meaning some by extracting named entities with the Standford NER
[7]
* identifying themes and clustering documents using MALLET [8]
Anybody with sets of texts can benefit from this workshop. Any corpus of
textual content is apropos: journal articles, books, the complete run of a
magazine, blog postings, Tweets, press releases, conference proceedings,
websites, poetry, etc. This workshop is computer (Windows, Linux, Macintosh)
agnostic. All the software used in this workshop is freely available on the
'Net, or it is already installed on one's computer. Active participation
requires zero programming, but students must bring their own computer, and they
must not be afraid of their computer's command line interface.
This workshop will not make participants an expert in natural language
processing, but it will empower them to make better sense of large sets of
textual information.
[1] Tika - http://tika.apache.org
[2] Voyant - http://voyant-tools.org
[3] AntConc - http://www.laurenceanthony.net/software/antconc/
[4] OpenRefine - http://openrefine.org
[5] Tableau Public - https://public.tableau.com/
[6] POS Tagger - https://nlp.stanford.edu/software/tagger.shtml
[7] NER - https://nlp.stanford.edu/software/CRF-NER.shtml
[8] MALLET - http://mallet.cs.umass.edu
