This course takes an introductory approach to machine learning in digital humanities topics. Participants will learn essential concepts in machine learning and use machine learning tools (including Mallet and Weka) to collect and analyze literary, historical, and social media data sets using a number of machine learning approaches. The course will include an optional introduction to the R programming language; knowledge of this language will provide students with an opportunity to develop their own machine learning algorithms. In addition to the technical dimension of machine learning, we will also discuss the hermeneutic challenges posed by machine learning to the digital humanities, particularly as technical decisions enable specific ways of engaging in humanities scholarship: In what ways do DH scholars need to be cautious about the ‘results’ offered by machine learning algorithms, and what is the relationship between those results and humanities forms of knowledge?
Neither programming expertise nor a computer science background are required. Students are encouraged to bring their own projects to the course in place of the provided data sets.