Course Qualitative corpus annotations, coding schemes and language models

Back

ECTS: 1

Course leader: Riccardo Fusaroli

Language: English

Graduate school: Faculty of Arts

Course fee: 0.00 DKK

Status: Course is open for application

Semester: Fall 2026

Application deadline: 25/10/2026

Cancellation deadline: 02/11/2026

Course type: Classroom teaching

Start date: 18/11/2026

Administrator: Andreas Mølgaard Laursen

Sign in to register

Allocation of seats

You will automatically be placed on a waiting list. After the application deadline, seats will be allocated and all applicants will be notified whether or not they have been offered a seat.

Please have a look in our FAQ

https://phd.arts.au.dk/phd-courses/courses/faq-phd-courses

Course description

In this course we tackle the delicate trade-offs in integrating language model driven annotations in research using qualitative manual annotations. The goal is to showcase how language technologies can be embedded in the annotation process, not only to learn from and scale up the annotation process, but also to critically think about the coding scheme and underlying constructs. In other words, we are interested in how qualitative and automated approaches can interact to provide better conceptual foundations for the annotations besides enabling larger corpora to be annotated.

The course is organized around a case study, which the students can access in advance, and group hands-on sessions.

Aim/Learning outcomes

By the end of the course, participants should:

  • Understand how language technologies can be critically integrated in annotation pipelines.
  • Be able to assess the main choices involved in LLM-based annotation, including model selection, prompt design, privacy, and human validation.
  • Understand the critical role of iterative refinements of coding schemes for both human and automated annotators, and of disagreements and error analyses.

Requirements for participation

  • Participants are expected to either have experience with corpus annotation or with language models.

Target group/Participants

  • PhD students within the domains of language sciences, language technologies, developmental psychology, cognitive science and related domains.

Workload

  • Course/ teaching hours: The course takes place over two days, 4 modules of 3h each
  • Preparation hours: The students have to familiarize themselves with the literature provided.
  • Written assignments etc.: There are hands-on assignment during the course, but none outside of the course.

Language 

  • English

Lecturers

  • Riccardo Fusaroli, Aarhus University

Literature

  • To be announced

Venue

  • - TBA

Course dates:

  • 18 November 2026 10:00 - 16:00
  • 25 November 2026 10:00 - 16:00