Housley, William  ORCID: https://orcid.org/0000-0003-1568-9093 and Dahl, Patrik
2024.
Membership categorisation, sociological description and role prompt engineering with ChatGPT.
Discourse and Communication
18
(6)
10.1177/17504813241267068
|
Preview |
PDF
- Published Version
Available under License Creative Commons Attribution Non-commercial. Download (495kB) | Preview |
Abstract
Large Language Models (LLMs) and generative Artificial Intelligence (A.I.) have become the latest disruptive digital technologies to breach the dividing lines between scientific endeavour and public consciousness. LLMs such as ChatGPT are platformed through commercial provid-ers such as OpenAI, which provide a conduit through which interaction is realised, via a series of exchanges in the form of written natural language text called ‘prompt engineering’. In this paper, we use Membership Categorisation Analysis to interrogate a collection of prompt engi-neering examples gathered from the endogenous ranking of prompting guides hosted on emerg-ing generative AI community and practitioner-relevant social media. We show how how both formal and vernacular ideas surrounding ‘natural’ sociological concepts are mobilised in order to configure LLMs for useful generative output. In addition, we identify some of the interac-tional limitations and affordances of using role prompt engineering for generating interactional stances with generative AI chatbots and (potentially) other formats. We conclude by reflecting the consequences of these everyday social-technical routines and the rise of ‘ethno-program-ming’ for generative AI that is realised through natural language and everyday sociological competencies.
| Item Type: | Article |
|---|---|
| Date Type: | Published Online |
| Status: | In Press |
| Schools: | Social Sciences (Includes Criminology and Education) |
| Publisher: | SAGE Publications |
| Date of First Compliant Deposit: | 22 May 2024 |
| Date of Acceptance: | 4 April 2024 |
| Last Modified: | 24 Nov 2024 22:19 |
| URI: | https://orca.cardiff.ac.uk/id/eprint/169092 |
Actions (repository staff only)
 |
Edit Item |
Altmetric
Altmetric
Cardiff University Information Services