Text as Data – PPOL 628#
Welcome to the open course content for Text as Data: the Road to Technical Language Processing!
This course is intended for those wanting to apply various modern text analysis techniques to gain domain-specific insights from their natural language data. Natural Language Processing (NLP) requires special care to apply in a useful, reproducible, and ethical way. This is especially true when context becomes a large factor in how the text is written or understood — for instance, technical fields like Social Science, Medicine, Engineering, Policy, Digital Humanities, and many more.
With that in mind, this course does not take a traditional, theory-heavy approach to the subject matter. Instead, the goal is to guide newcomers through the plethora of tools, theoretical assumptions, data types, and ethical questions that arise when NLP is used as descision-support for experts and decision makers. This is a class about how the broader NLP Socio-technical system can or even should function: Technical Language Processing.
For a more in-depth overview of the class, see the Syllabus. Alternatively, get started down the road to TLP by reading the Introduction!
Contributing#
These materials are open source, and all contributions that help improve its usefulness are welcome! To contribute…