An analysis of the generative AI use as analyst in qualitative research in science education

Detalhes bibliográficos
Autor(a) principal: Rodrigues dos Anjos, Juliana
Data de Publicação: 2024
Outros Autores: de Souza, Maira Giovana, Serrano de Andrade Neto, Agostinho, Campello de Souza, Bruno
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Revista Pesquisa Qualitativa (Online)
Texto Completo: https://editora.sepq.org.br/rpq/article/view/724
Resumo: The article evaluates the effectiveness of generative artificial intelligence models, specifically ChatGPT 4.0 and Claude 2.0, in conducting qualitative research within the field of scientific education. By applying the Cognitive Networks Mediation Theory (CNMT) to analyze interviews from two students, it was found that Claude 2.0 surpassed ChatGPT 4.0 in recognizing cognitive mediations and distinguishing between pre- and post-test conditions. Although both models concurred on the concept of conceptual evolution, Claude 2.0 demonstrated a greater capacity for detail, notably by referencing specific interview excerpts to support its analyses upon request. In contrast, ChatGPT 4.0 exhibited difficulties in these areas, even when given additional prompts. The study concludes by acknowledging the utility of AI, particularly Claude 2.0, for qualitative research, while also emphasizing the critical role of human oversight in detecting potential deficiencies within these models.
id SE&PQ-1_dcaaba5e3e2efdfa004817253a8124c3
oai_identifier_str oai:editora.sepq.org.br:article/724
network_acronym_str SE&PQ-1
network_name_str Revista Pesquisa Qualitativa (Online)
repository_id_str
spelling An analysis of the generative AI use as analyst in qualitative research in science educationUma análise do uso de IA generativa como investigadora em pesquisas qualitativas em educação científicaAnálise qualitativaEducação científicaTMCChatGPTClaudeQualitative analysisScience EducationCNMTChatGPTClaudeThe article evaluates the effectiveness of generative artificial intelligence models, specifically ChatGPT 4.0 and Claude 2.0, in conducting qualitative research within the field of scientific education. By applying the Cognitive Networks Mediation Theory (CNMT) to analyze interviews from two students, it was found that Claude 2.0 surpassed ChatGPT 4.0 in recognizing cognitive mediations and distinguishing between pre- and post-test conditions. Although both models concurred on the concept of conceptual evolution, Claude 2.0 demonstrated a greater capacity for detail, notably by referencing specific interview excerpts to support its analyses upon request. In contrast, ChatGPT 4.0 exhibited difficulties in these areas, even when given additional prompts. The study concludes by acknowledging the utility of AI, particularly Claude 2.0, for qualitative research, while also emphasizing the critical role of human oversight in detecting potential deficiencies within these models.O artigo avalia a eficácia de modelos de inteligência artificial generativa, especificamente ChatGPT 4.0 e Claude 2.0, na realização de pesquisas qualitativas na área de educação científica. Ao aplicar a Teoria da Mediação das Redes Cognitivas (CNMT) para analisar entrevistas de dois estudantes, constatou-se que Claude 2.0 superou o ChatGPT 4.0 na capacidade de reconhecer mediações cognitivas e distinguir entre condições de pré e pós-teste. Embora ambos os modelos tenham concordado sobre o conceito de evolução conceitual, Claude 2.0 demonstrou maior capacidade de detalhamento, notavelmente ao referenciar trechos específicos das entrevistas para apoiar suas análises quando solicitado. Em contraste, ChatGPT 4.0 exibiu dificuldades nessas áreas, mesmo quando fornecido com prompts adicionais. O estudo conclui reconhecendo a utilidade da IA, particularmente de Claude 2.0, para pesquisas qualitativas, enquanto também enfatiza o papel crítico da supervisão humana na detecção de potenciais deficiências dentro desses modelos.Sociedade de Estudos e Pesquisas Qualitativos - SE&PQ2024-04-30info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://editora.sepq.org.br/rpq/article/view/72410.33361/RPQ.2024.v.12.n.30.724Qualitative Research Journal ; Vol. 12 No. 30 (2024): Pesquisa Qualitativa e Inteligência Artificial (IA): Ética, Teorização, Métodos e Possibilidades; 01-29Revista Pesquisa Qualitativa; v. 12 n. 30 (2024): Pesquisa Qualitativa e Inteligência Artificial (IA): Ética, Teorização, Métodos e Possibilidades; 01-292525-82221809-025710.33361/RPQ.v.12.n.30reponame:Revista Pesquisa Qualitativa (Online)instname:Sociedade Brasileira de Estudos e Pesquisa Qualitativos (SE&PQ)instacron:SE&PQenghttps://editora.sepq.org.br/rpq/article/view/724/450Copyright (c) 2024 Revista Pesquisa Qualitativahttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccessRodrigues dos Anjos, Julianade Souza, Maira GiovanaSerrano de Andrade Neto, AgostinhoCampello de Souza, Bruno2024-05-01T05:33:17Zoai:editora.sepq.org.br:article/724Revistahttps://editora.sepq.org.br/index.php/rpq/indexONGhttps://editora.sepq.org.br/index.php/rpq/oai||revista.rpq@gmail.com2525-82221809-0257opendoar:2024-05-01T05:33:17Revista Pesquisa Qualitativa (Online) - Sociedade Brasileira de Estudos e Pesquisa Qualitativos (SE&PQ)false
dc.title.none.fl_str_mv An analysis of the generative AI use as analyst in qualitative research in science education
Uma análise do uso de IA generativa como investigadora em pesquisas qualitativas em educação científica
title An analysis of the generative AI use as analyst in qualitative research in science education
spellingShingle An analysis of the generative AI use as analyst in qualitative research in science education
Rodrigues dos Anjos, Juliana
Análise qualitativa
Educação científica
TMC
ChatGPT
Claude
Qualitative analysis
Science Education
CNMT
ChatGPT
Claude
title_short An analysis of the generative AI use as analyst in qualitative research in science education
title_full An analysis of the generative AI use as analyst in qualitative research in science education
title_fullStr An analysis of the generative AI use as analyst in qualitative research in science education
title_full_unstemmed An analysis of the generative AI use as analyst in qualitative research in science education
title_sort An analysis of the generative AI use as analyst in qualitative research in science education
author Rodrigues dos Anjos, Juliana
author_facet Rodrigues dos Anjos, Juliana
de Souza, Maira Giovana
Serrano de Andrade Neto, Agostinho
Campello de Souza, Bruno
author_role author
author2 de Souza, Maira Giovana
Serrano de Andrade Neto, Agostinho
Campello de Souza, Bruno
author2_role author
author
author
dc.contributor.author.fl_str_mv Rodrigues dos Anjos, Juliana
de Souza, Maira Giovana
Serrano de Andrade Neto, Agostinho
Campello de Souza, Bruno
dc.subject.por.fl_str_mv Análise qualitativa
Educação científica
TMC
ChatGPT
Claude
Qualitative analysis
Science Education
CNMT
ChatGPT
Claude
topic Análise qualitativa
Educação científica
TMC
ChatGPT
Claude
Qualitative analysis
Science Education
CNMT
ChatGPT
Claude
description The article evaluates the effectiveness of generative artificial intelligence models, specifically ChatGPT 4.0 and Claude 2.0, in conducting qualitative research within the field of scientific education. By applying the Cognitive Networks Mediation Theory (CNMT) to analyze interviews from two students, it was found that Claude 2.0 surpassed ChatGPT 4.0 in recognizing cognitive mediations and distinguishing between pre- and post-test conditions. Although both models concurred on the concept of conceptual evolution, Claude 2.0 demonstrated a greater capacity for detail, notably by referencing specific interview excerpts to support its analyses upon request. In contrast, ChatGPT 4.0 exhibited difficulties in these areas, even when given additional prompts. The study concludes by acknowledging the utility of AI, particularly Claude 2.0, for qualitative research, while also emphasizing the critical role of human oversight in detecting potential deficiencies within these models.
publishDate 2024
dc.date.none.fl_str_mv 2024-04-30
dc.type.driver.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
format article
status_str publishedVersion
dc.identifier.uri.fl_str_mv https://editora.sepq.org.br/rpq/article/view/724
10.33361/RPQ.2024.v.12.n.30.724
url https://editora.sepq.org.br/rpq/article/view/724
identifier_str_mv 10.33361/RPQ.2024.v.12.n.30.724
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv https://editora.sepq.org.br/rpq/article/view/724/450
dc.rights.driver.fl_str_mv Copyright (c) 2024 Revista Pesquisa Qualitativa
https://creativecommons.org/licenses/by/4.0
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Copyright (c) 2024 Revista Pesquisa Qualitativa
https://creativecommons.org/licenses/by/4.0
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Sociedade de Estudos e Pesquisas Qualitativos - SE&PQ
publisher.none.fl_str_mv Sociedade de Estudos e Pesquisas Qualitativos - SE&PQ
dc.source.none.fl_str_mv Qualitative Research Journal ; Vol. 12 No. 30 (2024): Pesquisa Qualitativa e Inteligência Artificial (IA): Ética, Teorização, Métodos e Possibilidades; 01-29
Revista Pesquisa Qualitativa; v. 12 n. 30 (2024): Pesquisa Qualitativa e Inteligência Artificial (IA): Ética, Teorização, Métodos e Possibilidades; 01-29
2525-8222
1809-0257
10.33361/RPQ.v.12.n.30
reponame:Revista Pesquisa Qualitativa (Online)
instname:Sociedade Brasileira de Estudos e Pesquisa Qualitativos (SE&PQ)
instacron:SE&PQ
instname_str Sociedade Brasileira de Estudos e Pesquisa Qualitativos (SE&PQ)
instacron_str SE&PQ
institution SE&PQ
reponame_str Revista Pesquisa Qualitativa (Online)
collection Revista Pesquisa Qualitativa (Online)
repository.name.fl_str_mv Revista Pesquisa Qualitativa (Online) - Sociedade Brasileira de Estudos e Pesquisa Qualitativos (SE&PQ)
repository.mail.fl_str_mv ||revista.rpq@gmail.com
_version_ 1798329747160170496

Registros relacionados