Updating 'The Future of Coding': Qualitative Coding with Generative Large Language Models
Uloženo v:
| Název: | Updating 'The Future of Coding': Qualitative Coding with Generative Large Language Models |
|---|---|
| Jazyk: | English |
| Autoři: | Nga Than (ORCID |
| Zdroj: | Sociological Methods & Research. 2025 54(3):849-888. |
| Dostupnost: | SAGE Publications. 2455 Teller Road, Thousand Oaks, CA 91320. Tel: 800-818-7243; Tel: 805-499-9774; Fax: 800-583-2665; e-mail: journals@sagepub.com; Web site: https://sagepub.com |
| Peer Reviewed: | Y |
| Page Count: | 40 |
| Datum vydání: | 2025 |
| Druh dokumentu: | Journal Articles Reports - Research |
| Descriptors: | Artificial Intelligence, Coding, Qualitative Research, Cues, Open Source Technology, Accuracy, Natural Language Processing, Social Science Research |
| DOI: | 10.1177/00491241251339188 |
| ISSN: | 0049-1241 1552-8294 |
| Abstrakt: | Over the past decade, social scientists have adapted computational methods for qualitative text analysis, with the hope that they can match the accuracy and reliability of hand coding. The emergence of GPT and open-source generative large language models (LLMs) has transformed this process by shifting from programming to engaging with models using natural language, potentially mimicking the in-depth, inductive, and/or iterative process of qualitative analysis. We test the ability of generative LLMs to replicate and augment traditional qualitative coding, experimenting with multiple prompt structures across four closed- and open-source generative LLMs and proposing a workflow for conducting qualitative coding with generative LLMs. We find that LLMs can perform nearly as well as prior supervised machine learning models in accurately matching hand-coding output. Moreover, using generative LLMs as a natural language interlocutor closely replicates traditional qualitative methods, indicating their potential to transform the qualitative research process, despite ongoing challenges. |
| Abstractor: | As Provided |
| Entry Date: | 2025 |
| Přístupové číslo: | EJ1475799 |
| Databáze: | ERIC |
Nájsť tento článok vo Web of Science | Abstrakt: | Over the past decade, social scientists have adapted computational methods for qualitative text analysis, with the hope that they can match the accuracy and reliability of hand coding. The emergence of GPT and open-source generative large language models (LLMs) has transformed this process by shifting from programming to engaging with models using natural language, potentially mimicking the in-depth, inductive, and/or iterative process of qualitative analysis. We test the ability of generative LLMs to replicate and augment traditional qualitative coding, experimenting with multiple prompt structures across four closed- and open-source generative LLMs and proposing a workflow for conducting qualitative coding with generative LLMs. We find that LLMs can perform nearly as well as prior supervised machine learning models in accurately matching hand-coding output. Moreover, using generative LLMs as a natural language interlocutor closely replicates traditional qualitative methods, indicating their potential to transform the qualitative research process, despite ongoing challenges. |
|---|---|
| ISSN: | 0049-1241 1552-8294 |
| DOI: | 10.1177/00491241251339188 |