Automating Thematic Analysis: How LLMs Analyse Controversial Topics

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Khan, Awais Hameed, Kegalle, Hiruni, D'Silva, Rhea, Watt, Ned, Whelan-Shamy, Daniel, Ghahremanlou, Lida, Magee, Liam
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914951482834944
author Khan, Awais Hameed
Kegalle, Hiruni
D'Silva, Rhea
Watt, Ned
Whelan-Shamy, Daniel
Ghahremanlou, Lida
Magee, Liam
author_facet Khan, Awais Hameed
Kegalle, Hiruni
D'Silva, Rhea
Watt, Ned
Whelan-Shamy, Daniel
Ghahremanlou, Lida
Magee, Liam
contents Large Language Models (LLMs) are promising analytical tools. They can augment human epistemic, cognitive and reasoning abilities, and support 'sensemaking', making sense of a complex environment or subject by analysing large volumes of data with a sensitivity to context and nuance absent in earlier text processing systems. This paper presents a pilot experiment that explores how LLMs can support thematic analysis of controversial topics. We compare how human researchers and two LLMs GPT-4 and Llama 2 categorise excerpts from media coverage of the controversial Australian Robodebt scandal. Our findings highlight intriguing overlaps and variances in thematic categorisation between human and machine agents, and suggest where LLMs can be effective in supporting forms of discourse and thematic analysis. We argue LLMs should be used to augment, and not replace human interpretation, and we add further methodological insights and reflections to existing research on the application of automation to qualitative research methods. We also introduce a novel card-based design toolkit, for both researchers and practitioners to further interrogate LLMs as analytical tools.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06919
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Automating Thematic Analysis: How LLMs Analyse Controversial Topics
Khan, Awais Hameed
Kegalle, Hiruni
D'Silva, Rhea
Watt, Ned
Whelan-Shamy, Daniel
Ghahremanlou, Lida
Magee, Liam
Computers and Society
Computation and Language
K.4.2
Large Language Models (LLMs) are promising analytical tools. They can augment human epistemic, cognitive and reasoning abilities, and support 'sensemaking', making sense of a complex environment or subject by analysing large volumes of data with a sensitivity to context and nuance absent in earlier text processing systems. This paper presents a pilot experiment that explores how LLMs can support thematic analysis of controversial topics. We compare how human researchers and two LLMs GPT-4 and Llama 2 categorise excerpts from media coverage of the controversial Australian Robodebt scandal. Our findings highlight intriguing overlaps and variances in thematic categorisation between human and machine agents, and suggest where LLMs can be effective in supporting forms of discourse and thematic analysis. We argue LLMs should be used to augment, and not replace human interpretation, and we add further methodological insights and reflections to existing research on the application of automation to qualitative research methods. We also introduce a novel card-based design toolkit, for both researchers and practitioners to further interrogate LLMs as analytical tools.
title Automating Thematic Analysis: How LLMs Analyse Controversial Topics
topic Computers and Society
Computation and Language
K.4.2
url https://arxiv.org/abs/2405.06919