From laborious to lucid: best practice for using generative AI for thematic and sentiment analysis

Nataliya Kocheva; Elena Fitkov-Norris

From laborious to lucid: best practice for using generative AI for thematic and sentiment analysis

Research output: Contribution to conference › Paper › peer-review

Abstract

Thematic analysis, a cornerstone of qualitative research, often entails laborious procedures. Recent strides in Generative AI, such as ChatGPT, offer promising avenues for refining qualitative data analysis. This study probes the effectiveness of ChatGPT as a tool for enhancing thematic and sentiment analysis. Through 4 semi-structured interviews and 200 customer reviews from Trustpilot, we unearthed opportunities, challenges and reservations regarding ChatGPT's integration into qualitative analysis in social science. We suggest best practices for prompt engineering to augment generative AI‘s role in thematic analysis. Results indicate that generative AI closely matches human-generated themes, providing an effective tool, capable of supporting thematic and sentiment analysis in social science research.

Original language	English
Publication status	Published - 21 Jun 2024
Event	FBSS Research Conference - Kingston upon Thames, U.K. Duration: 21 Jun 2024 → 21 Jun 2024

Conference

Conference	FBSS Research Conference
Period	21/06/24 → 21/06/24

Bibliographical note

Organising Body: Kingston University

Keywords

Business and management studies

Cite this

@conference{eb39b50ef5f642b694b488050901413e,

title = "From laborious to lucid: best practice for using generative AI for thematic and sentiment analysis",

abstract = "Thematic analysis, a cornerstone of qualitative research, often entails laborious procedures. Recent strides in Generative AI, such as ChatGPT, offer promising avenues for refining qualitative data analysis. This study probes the effectiveness of ChatGPT as a tool for enhancing thematic and sentiment analysis. Through 4 semi-structured interviews and 200 customer reviews from Trustpilot, we unearthed opportunities, challenges and reservations regarding ChatGPT's integration into qualitative analysis in social science. We suggest best practices for prompt engineering to augment generative AI{\textquoteleft}s role in thematic analysis. Results indicate that generative AI closely matches human-generated themes, providing an effective tool, capable of supporting thematic and sentiment analysis in social science research.",

keywords = "Business and management studies",

author = "Nataliya Kocheva and Elena Fitkov-Norris",

note = "Organising Body: Kingston University; FBSS Research Conference ; Conference date: 21-06-2024 Through 21-06-2024",

year = "2024",

month = jun,

day = "21",

language = "English",

}

TY - CONF

T1 - From laborious to lucid

T2 - FBSS Research Conference

AU - Kocheva, Nataliya

AU - Fitkov-Norris, Elena

N1 - Organising Body: Kingston University

PY - 2024/6/21

Y1 - 2024/6/21

N2 - Thematic analysis, a cornerstone of qualitative research, often entails laborious procedures. Recent strides in Generative AI, such as ChatGPT, offer promising avenues for refining qualitative data analysis. This study probes the effectiveness of ChatGPT as a tool for enhancing thematic and sentiment analysis. Through 4 semi-structured interviews and 200 customer reviews from Trustpilot, we unearthed opportunities, challenges and reservations regarding ChatGPT's integration into qualitative analysis in social science. We suggest best practices for prompt engineering to augment generative AI‘s role in thematic analysis. Results indicate that generative AI closely matches human-generated themes, providing an effective tool, capable of supporting thematic and sentiment analysis in social science research.

AB - Thematic analysis, a cornerstone of qualitative research, often entails laborious procedures. Recent strides in Generative AI, such as ChatGPT, offer promising avenues for refining qualitative data analysis. This study probes the effectiveness of ChatGPT as a tool for enhancing thematic and sentiment analysis. Through 4 semi-structured interviews and 200 customer reviews from Trustpilot, we unearthed opportunities, challenges and reservations regarding ChatGPT's integration into qualitative analysis in social science. We suggest best practices for prompt engineering to augment generative AI‘s role in thematic analysis. Results indicate that generative AI closely matches human-generated themes, providing an effective tool, capable of supporting thematic and sentiment analysis in social science research.

KW - Business and management studies

M3 - Paper

Y2 - 21 June 2024 through 21 June 2024

ER -

From laborious to lucid: best practice for using generative AI for thematic and sentiment analysis

Abstract

Conference

Bibliographical note

Keywords

Fingerprint

Cite this