Invitation to the first of three EM/CA ‘promptathons’, 3rd July, Cardiff.
Date: Thursday, 3rd July 2025 Location: Hybrid – In person at Cardiff University, UK & Online via Zoom (register here).
Join us for the first in a series of three events that aim to explore Ethnomethodological and Conversation Analytic (EM/CA) approaches to Large Language Models (LLMs). The event will bring together researchers to ask how principles, methods, and emerging study designs within EMCA can examine the interactional dynamics and conceptual puzzles posed by technologies that “travel under the sign of AI” (Suchman 2023).
The workshop will include an introduction to GailBot – a software tool that allows researchers to use machine learning methods for CA transcription.
Background
The types of LLMs that are an increasingly ubiquitous part of everyday technology use are all, in more or less explicit ways, based on the instructional format of the ‘prompt’. In some cases, an LLM prompt may be knowingly composed by an ‘end-user’ (e.g., using a ‘chat’ interface). In others, the prompt may be constructed ‘back-stage’ by a designer, shaping the linguistic context for subsequent linguistic contributions by a ‘naïve user’.
Fundamentally, this complex range of socio-technical practices for manipulating and configuring the outputs of LLMs (‘prompt engineering’) are dealing with praxeological issues and so lend themselves to ethnomethodological inquiry (Housley & Dahl, 2024).
This workshop will draw on EM/CA’s focus on naturally occurring interaction and its moral/social orders to find ways to explore, evaluate, and understand ‘prompting’ as a practice, as a setting for studies of various forms of work, and as an empirical material.
First Pair Prompt is intended to be the first of three events, with at least two subsequent meetings that will build upon the discussions and collaborations initiated here, with the likely outcome being a publication, a special issue, or some other research output.
Key Themes and Topics:
Building on a recent special issue of discourse and communication (Albert & Hall, 2024), First Pair Prompt aims explore the critical intersections of EM/CA and ‘AI’, drawing on 60 years of interactional studies to understand, for example:
- Repair practices in human-LLM interaction (Pütz & Esposito, 2024)
- Ascriptions and agency attributions (Albert and Hall, 2024; Pelikan et al. 2022)
- Prompt engineering as a member’s practice (Housley & Dahl, 2024)
- Action-oriented evaluation of LLMs (Liesenfeld & Dingemanse, 2024)
- Recipient design in human-LLM interaction (Tuncer et al., 2023)
- The situated nature of human-LLM interaction (Rudaz & Licoppe, 2024)
First Pair Prompt is an invitation-based workshop, but we are also inviting you to share it with other EM/CA scholars who may be interested in expanding on the topics above.
References
Albert, S., & Hall, L. (2024). Distributed agency in smart homecare interactions: A conversation analytic case study. Discourse & Communication, 18(6), 892–904. https://doi.org/10.1177/17504813241267059
Housley, W., & Dahl, P. (2024). Membership categorisation, sociological description and role prompt engineering with ChatGPT. Discourse & Communication, 17504813241267068. https://doi.org/10.1177/17504813241267068
Liesenfeld, A., & Dingemanse, M. (2024). Interactive probes: Towards action-level evaluation for dialogue systems. Discourse & Communication, 17504813241267071. https://doi.org/10.1177/17504813241267071
Pelikan, H., Broth, M., & Keevallik, L. (2022). When a Robot Comes to Life: The Interactional Achievement of Agency as a Transient Phenomenon. Social Interaction. Video-Based Studies of Human Sociality, 5(3), Article 3. https://doi.org/10.7146/si.v5i3.129915
Pütz, O., & Esposito, E. (2024). Performance without understanding: How ChatGPT relies on humans to repair conversational trouble. Discourse & Communication, 17504813241271492. https://doi.org/10.1177/17504813241271492
Rudaz, D., & Licoppe, C. (2024). ‘Playing the robot’s advocate’: Bystanders’ descriptions of a robot’s conduct in public settings. Discourse & Communication, 17504813241271481. https://doi.org/10.1177/17504813241271481
Suchman, L. (2023). The uncontroversial ‘thingness’ of AI. Big Data & Society, 10(2), 20539517231206794. https://doi.org/10.1177/20539517231206794
Tuncer, S., Licoppe, C., Luff, P., & Heath, C. (2023). Recipient design in human–robot interaction: The emergent assessment of a robot’s competence. AI & SOCIETY. https://doi.org/10.1007/s00146-022-01608-7
Umair, M., Mertens, J. B., Albert, S., & Ruiter, J. P. de. (2022). GailBot: An automatic transcription system for Conversation Analysis. Dialogue & Discourse, 13(1), Article 1. https://doi.org/10.5210/dad.2022.103