Tel: +49 (0221) 47694 - 166
Tel: +49 (0221) 47694 - 166
Research Factory for Text Mining in the Social Sciences
Prof. Dr. Gerhard Heyer, Christian Kahmann, Kenan Erdogan, Dr. Arnim Bleier
Date: 23.03 - 25.03.2020 ics-file
Location: Cologne Course language: English
The three-day workshop serves as a research incubator linking the use of web-based Natural Language Processing tools with challenges and research questions of the Social Sciences. The workshop is intended to provide participants with insights into the technologies of Text Mining Infrastructures and their use. In more detail, it will enable Social Scientists to address specific questions that require text processing based operationalization. The participants will be shown theories and methods, which will then be adapted to their questions in intensive supervision. The offered infrastructure environment includes the iLCM, an integrated virtualized text mining infrastructure and Open Research Computing environment, which enables the combined use of GUI and scripting based analysis procedures. We expect our participants to prepare a research question, which we discuss together during the workshop and try to operationalize. The use of participants own datasets is possible in consultation with the organizers.
How to apply and register for the Workshop:
To enable an intensive mentoring of the participants and their projects during the workshop a 2-step registration process is used.
Step 1: Interested potential participants write a short letter of motivation together with a brief description of a project idea they want to pursue during the workshop to Christian Kahmann (email@example.com). The letters of motivation and project ideas will then be reviewed by the lecturers and suitable candidates will get a notice of admission.
Once you have received your notice of admission you can register on this platform for the workshop.
The participants will be able to operationalize a scientific question through the use of methods of Natural Language Processing with the conclusion of the workshop. Furthermore, the combined use of R and GUI based tools will be explained and learned using participants questions. This can include the understanding of methods like Topic Modeling, Co-occurrence Statistics or Keyword Extraction as well as the implementation of the processing strategies in R.
The participants should have their own research questions which requires the use of Natural Language Processing which can be discussed and realized during the workshop. Furthermore, knowledge of R is recommended for the extension of GUI based analysis techniques, but is not mandatory.
Please note that participants have to bring their own laptop for this course. All utilized software is available without cost as open source under Windows, MacOS, and Linux systems. Detailed installation instructions for the suggested development environments will be provided before the start of the course.