Welcome to Cultural and Literary Text Mining. As suggested by its title, this study group is where we learn and explore how to apply computational methods to the study of literature and culture. We look at the methodological debate of this “quantitative turn”, the tools and practices of which are becoming fundamental to the field now known as digital humanities. How does text mining inform literary and cultural studies? In a discipline that privileges close reading, what do people think about computational methods? What do we need to know to conduct data-driven research on literature and culture? What does a typical research project involve? We seek to nd some answers to those questions here.
Although it’s called a study group, you may very well think of it as a student-initiated (Kent being the student), student-led, 15-credit postgraduate taught MA + MSc module. We will proceed in form of:
- mini-lecture and seminar (theory), where a reader (Kent by default) tries to highlight key argu- ments in readings for each session, and participants may share their opinions on and questions for them (if they have read them in advance, which is not strictly required)
- Python workshop (practical), in which we rst learn the basics of Python by making connections with JavaScript/PHP, and then try some tasks typically involved in a text mining project.
I imagine we will go through three major phases:
- Phase I: emphasis on relevant theories + Python basics
- Phase II: emphasis on practical text mining skills in Python + related academic projects
For more information, take a look at this general introduction.
Coordinator: Kent Kai-hsiung Chang (MA/MSc student in Digital Humanities, DIS, UCL)
Moodle
We have set up a Moodle platform to accomodate participants who are not/refuse to be on Facebook and facilitate online discussion and circulation of materials for our purpose. Simiple registration is required. Participants are strongly encouraged to have access to Moodle.
