Workshop hosted by the Digital Humanities Lab of the University of Freiburg

Many researchers in the fields of Conversation Analysis and Interactional Linguistics painstakingly elaborate transcripts and manually implement annotations in ELAN, a software for multimodal annotation. Few researchers, however, seem to know how to post-process this immensely valuable data in a way that allows synthesis, aggregation, transformation, large-scale analysis and visualization. This workshop aims to present some solutions for these tasks implemented in R and based on Regular Expression (or regex), a syntax used to match, select, edit, and extract data and to reshape data frames based on regularities (patterns) in the data.

The full-day workshop will cover these topics:

– Basics of R and regex (Crash Course)
– Convert (multimodal) transcripts to R data frames to make them machine-readable
– Analyze (multimodal) transcripts in R data frames
– Export and structure ELAN annotations in R data frames
– Analyze and visualize ELAN annotations in R data frames

The workshop is open to beginners and more experienced users of R. To facilitate a running start for everybody, the workshop will start with a crash course on the key syntactic elements of regex and some key R functions before we turn to using them for Multimodal Analysis. The workshop aims for maximum relevance to the participants: participants are encouraged to articulate to the instructor what special tasks they wish to achieve with their data prior to the workshop (no later than 9 May, 2025). Concrete solutions to these tasks could be discussed during the workshop.

The maximum number of participants is 25; the registration deadline is 9 May, 2025; participation is free. To register (and, if you want, share your data) please contact: chrisruehlemann@gmail.com