arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.13014cs.CL
收藏

大型语言模型能否模拟半结构化访谈的归纳式主题分析?关于该方法与模型局限的探索与 provocations

Can Large Language Models emulate an inductive Thematic Analysis of semi-structured interviews? An exploration and provocation on the limits of the approach and the model

Abertay University(阿伯泰大学)

Stefano De Paoli

AI总结:

本文探索 GPT 3.5-Turbo 模拟归纳式主题分析的可行性,通过两个半结构化访谈数据集对比既有人类分析,发现其可部分识别主要主题,但定位为质性研究辅助而非替代人类分析者。

摘要:

大型语言模型(LLM)已成为强大的生成式人工智能解决方案,可应用于多个领域和工作方向。本文介绍了一项实验的结果与反思,该实验使用 GPT 3.5-Turbo 模型模拟归纳式主题分析的某些方面。此前关于该主题的研究主要集中在开展演绎式分析。主题分析是社会科学中常用的质性分析方法,其基础是人类分析者所作的解释,以及对质性数据中显性和潜在意义的识别。尝试用 LLM 进行基于人类解释的分析显然是一种挑衅,但也是了解这些系统在质性研究中能否使用以及如何使用的一种途径。本文阐述了尝试这种模拟的动机,反思了 Braun 和 Clarke 提出的主题分析六步骤如何至少能在 LLM 中得到部分复现,并思考了模型产生的输出是什么。论文使用了两个已有的开放获取半结构化访谈数据集,这些数据集此前已由其他研究者用主题分析进行过分析。研究将先前完成的分析(及相关主题)与 LLM 产生的结果进行比较。结果表明,该模型至少能部分推断出一些主要主题。本文的目的不是在质性分析中取代人类分析者,而是了解 LLM 数据处理的某些要素能否在一定程度上为质性研究提供支持。

英文摘要:

Large Language Models (LLMs) have emerged as powerful generative Artificial Intelligence solutions which can be applied to several fields and areas of work. This paper presents results and reflection of an experiment done to use the model GPT 3.5-Turbo to emulate some aspects of an inductive Thematic Analysis. Previous research on this subject has largely worked on conducting deductive analysis. Thematic Analysis is a qualitative method for analysis commonly used in social sciences and it is based on interpretations made by the human analyst(s) and the identification of explicit and latent meanings in qualitative data. Attempting an analysis based on human interpretation with an LLM clearly is a provocation but also a way to learn something about how these systems can or cannot be used in qualitative research. The paper presents the motivations for attempting this emulation, it reflects on how the six steps to a Thematic Analysis proposed by Braun and Clarke can at least partially be reproduced with the LLM and it also reflects on what are the outputs produced by the model. The paper used two existing datasets of open access semi-structured interviews, previously analysed with Thematic Analysis by other researchers. It used the previously produced analysis (and the related themes) to compare with the results produced by the LLM. The results show that the model can infer at least partially some of the main Themes. The objective of the paper is not to replace human analysts in qualitative analysis but to learn if some elements of LLM data manipulation can to an extent be of support for qualitative research.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑