Evaluating generative AI for qualitative data extraction in community-based fisheries management literature

Abstract Uptake of AI tools in knowledge production processes is rapidly growing. In this pilot study, we explore the ability of generative AI tools to reliably extract qualitative data from a limited sample of peer-reviewed documents in the context of community-based fisheries management (CBFM) lit...

Full description

Saved in:
Bibliographic Details
Main Authors: S. Spillias, K. M. Ollerhead, M. Andreotta, R. Annand-Jones, F. Boschetti, J. Duggan, D. B. Karcher, C. Paris, R. J. Shellock, R. Trebilco
Format: Article
Language:English
Published: BMC 2025-06-01
Series:Environmental Evidence
Subjects:
Online Access:https://doi.org/10.1186/s13750-025-00362-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850223793024270336
author S. Spillias
K. M. Ollerhead
M. Andreotta
R. Annand-Jones
F. Boschetti
J. Duggan
D. B. Karcher
C. Paris
R. J. Shellock
R. Trebilco
author_facet S. Spillias
K. M. Ollerhead
M. Andreotta
R. Annand-Jones
F. Boschetti
J. Duggan
D. B. Karcher
C. Paris
R. J. Shellock
R. Trebilco
author_sort S. Spillias
collection DOAJ
description Abstract Uptake of AI tools in knowledge production processes is rapidly growing. In this pilot study, we explore the ability of generative AI tools to reliably extract qualitative data from a limited sample of peer-reviewed documents in the context of community-based fisheries management (CBFM) literature. Specifically, we evaluate the capacity of multiple AI tools to analyse 33 CBFM papers and extract relevant information for a systematic literature review, comparing the results to those of human reviewers. We address how well AI tools can discern the presence of relevant contextual data, whether the outputs of AI tools are comparable to human extractions, and whether the difficulty of question influences the performance of the extraction. While the AI tools we tested (GPT4-Turbo and Elicit) were not reliable in discerning the presence or absence of contextual data, at least one of the AI tools consistently returned responses that were on par with human reviewers. These results highlight the potential utility of AI tools in the extraction phase of evidence synthesis for supporting human-led reviews, while underscoring the ongoing need for human oversight. This exploratory investigation provides initial insights into the current capabilities and limitations of AI in qualitative data extraction within the specific domain of CBFM, laying groundwork for future, more comprehensive evaluations across diverse fields and larger datasets.
format Article
id doaj-art-429032bfbb894972b82fa4ec89fbf91e
institution OA Journals
issn 2047-2382
language English
publishDate 2025-06-01
publisher BMC
record_format Article
series Environmental Evidence
spelling doaj-art-429032bfbb894972b82fa4ec89fbf91e2025-08-20T02:05:49ZengBMCEnvironmental Evidence2047-23822025-06-0114111810.1186/s13750-025-00362-9Evaluating generative AI for qualitative data extraction in community-based fisheries management literatureS. Spillias0K. M. Ollerhead1M. Andreotta2R. Annand-Jones3F. Boschetti4J. Duggan5D. B. Karcher6C. Paris7R. J. Shellock8R. Trebilco9CSIRO EnvironmentCentre for Marine Socioecology, University of TasmaniaCSIRO EnvironmentCSIRO EnvironmentCSIRO EnvironmentFenner School of Environment and Society, Australian National UniversityAustralian National Centre for the Public Awareness of Science, Australian National UniversityCSIRO Data61Centre for Marine Socioecology, University of TasmaniaCSIRO EnvironmentAbstract Uptake of AI tools in knowledge production processes is rapidly growing. In this pilot study, we explore the ability of generative AI tools to reliably extract qualitative data from a limited sample of peer-reviewed documents in the context of community-based fisheries management (CBFM) literature. Specifically, we evaluate the capacity of multiple AI tools to analyse 33 CBFM papers and extract relevant information for a systematic literature review, comparing the results to those of human reviewers. We address how well AI tools can discern the presence of relevant contextual data, whether the outputs of AI tools are comparable to human extractions, and whether the difficulty of question influences the performance of the extraction. While the AI tools we tested (GPT4-Turbo and Elicit) were not reliable in discerning the presence or absence of contextual data, at least one of the AI tools consistently returned responses that were on par with human reviewers. These results highlight the potential utility of AI tools in the extraction phase of evidence synthesis for supporting human-led reviews, while underscoring the ongoing need for human oversight. This exploratory investigation provides initial insights into the current capabilities and limitations of AI in qualitative data extraction within the specific domain of CBFM, laying groundwork for future, more comprehensive evaluations across diverse fields and larger datasets.https://doi.org/10.1186/s13750-025-00362-9Artificial IntelligenceSystematic reviewLarge language modelsScientific publicationNatural-language processingFuture of science
spellingShingle S. Spillias
K. M. Ollerhead
M. Andreotta
R. Annand-Jones
F. Boschetti
J. Duggan
D. B. Karcher
C. Paris
R. J. Shellock
R. Trebilco
Evaluating generative AI for qualitative data extraction in community-based fisheries management literature
Environmental Evidence
Artificial Intelligence
Systematic review
Large language models
Scientific publication
Natural-language processing
Future of science
title Evaluating generative AI for qualitative data extraction in community-based fisheries management literature
title_full Evaluating generative AI for qualitative data extraction in community-based fisheries management literature
title_fullStr Evaluating generative AI for qualitative data extraction in community-based fisheries management literature
title_full_unstemmed Evaluating generative AI for qualitative data extraction in community-based fisheries management literature
title_short Evaluating generative AI for qualitative data extraction in community-based fisheries management literature
title_sort evaluating generative ai for qualitative data extraction in community based fisheries management literature
topic Artificial Intelligence
Systematic review
Large language models
Scientific publication
Natural-language processing
Future of science
url https://doi.org/10.1186/s13750-025-00362-9
work_keys_str_mv AT sspillias evaluatinggenerativeaiforqualitativedataextractionincommunitybasedfisheriesmanagementliterature
AT kmollerhead evaluatinggenerativeaiforqualitativedataextractionincommunitybasedfisheriesmanagementliterature
AT mandreotta evaluatinggenerativeaiforqualitativedataextractionincommunitybasedfisheriesmanagementliterature
AT rannandjones evaluatinggenerativeaiforqualitativedataextractionincommunitybasedfisheriesmanagementliterature
AT fboschetti evaluatinggenerativeaiforqualitativedataextractionincommunitybasedfisheriesmanagementliterature
AT jduggan evaluatinggenerativeaiforqualitativedataextractionincommunitybasedfisheriesmanagementliterature
AT dbkarcher evaluatinggenerativeaiforqualitativedataextractionincommunitybasedfisheriesmanagementliterature
AT cparis evaluatinggenerativeaiforqualitativedataextractionincommunitybasedfisheriesmanagementliterature
AT rjshellock evaluatinggenerativeaiforqualitativedataextractionincommunitybasedfisheriesmanagementliterature
AT rtrebilco evaluatinggenerativeaiforqualitativedataextractionincommunitybasedfisheriesmanagementliterature