Scholars across multiple disciplines are finding themselves face-to-face with massive amounts of digitized data. In the humanities and many social science disciplines, this data is often in the form of unstructured text. This course will introduce students to cutting edge ways of structuring and analyzing digitized text-as-data, and will do so by exploring questions fundamental to the humanities. The ultimate goal is to encourage students to think about novel ways they can apply these techniques to their own data and research questions, and to provide the skills necessary to apply the methods in their own research. We will use the open source (and free!) programming language Python. We will also provide demonstration corpora.
- Principles of Natural Language Processing
- Introduction to Python for NLP
- Discriminating Words
- Dictionary Methods
- Textual Classification
- Word Embedding
This workshop will be taught in the open source programming language Python. Participants should install Anaconda for Python 3.6 on their laptops prior to the first class.
- Ted Underwood. Seven ways humanists are using computers to understand text
- H. Andrew Schwartz and Lyle H. Ungar (2015). Data-Driven Content Analysis of Social Media: A Systematic Overview of Automated Methods