CLASS-L Archives

April 2012


Options: Use Proportional Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Christine Arnold <[log in to unmask]>
Reply To:
Classification, clustering, and phylogeny estimation
Mon, 2 Apr 2012 13:38:23 -0700
text/plain (60 lines)
Post-Doc for Text Classification

Applications are invited for a Post Doc position for Text
Classification for interdisciplinary research within the project
"Database on Political Responsiveness". The project is funded by
the Dutch Organisation for Scientific Research (NWO). The
principal investigators are Christine Arnold, Maastricht
University, Mark Franklin, Massachusetts Institute of Technology,
and Christopher Wlezien, Temple University.

One set of tasks relates to the harvesting of data from the
deep-web, for instance from governmental websites. The Post Doc
will write customized scripts to accommodate the disparate
structures of these websites, while bringing an understanding of
the substantive political science questions to the task.
Additionally, the Post Doc will apply ontology alignment tools
for the coding of the policy documents and for semantic matching
driven by machine learning. This will be done to richly
cross-index and hyperlink the data both in terms of semantic
relevance, as well as from a point of view of temporal continuity
and time-series.

The position also includes responsibilities for working with the
compute-cluster used for the project, its networking, its primary
storage and backup storage sub-systems, and for the routine
monitoring of system health. Experience with Linux is a definite

The candidate has obtained a PhD degree or his/her dissertation
is approved by the reading committee.

We are looking for a candidate who has:
* a strong background in computer science related to knowledge
representation, information retrieval systems, and web-harvesting
of diverse data types.
* experience with ontology matching and natural language
* experience with data harmonization and cross-linking of
different data types.
* experience with relational databases and import and export of
data to SQL,SPSS, STATA, and R.
* programming skills which must include scripting environments
such as Perl or Python, relational database technologies such as
* excellent written and verbal communication skills in English.
* the ability to contribute proactively to the conduct of the
project and work with an interdisciplinary team as a team-player.

Closing date for applications is April 16th, 2012.

Interested candidates are invited to contact Christine Arnold:
[log in to unmask]

CLASS-L list.