亲爱的研友该休息了!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您度过漫漫科研夜!身体可是革命的本钱,早点休息,好梦!

Large Language Models in Qualitative Analysis: Comparing Traditional and Researcher-Interpreted Approaches

主题分析 计算机科学 定性研究 叙述的 背景(考古学) 定性性质 数据科学 可扩展性 推论 自然语言处理 语用学 语篇分析 定性分析 专题地图 规范性 人工智能 知识管理 可视化 心理学 编码(社会科学) 医疗保健 提升(金属加工) 管理科学 钥匙(锁) 工作(物理)
作者
Ranjita Misra,Rajashree Dahal,Brenna Kirk,Raihan Khan,Gizem Dogan,Robin Chataut,Prashnna Gyawali
出处
期刊:International journal of qualitative methods [SAGE Publishing]
卷期号:25 被引量:7
标识
DOI:10.1177/16094069261426100
摘要

Qualitative data analysis, particularly thematic analysis, is a widely used method for uncovering patterns and insights in narrative data but often faces challenges such as being resource-intensive and susceptible to researcher bias. In recent years, Large Language Models (LLMs) have emerged as promising tools to assist human coders in conducting thematic analysis, offering efficiency and scalability in processing large datasets. However, existing work primarily relies on tools like ChatGPT, raising privacy concerns—especially when analyzing sensitive healthcare data—and lacks systematic validation through comparisons with human coders. This study aims to evaluate the potential of open-source LLMs for qualitative data analysis. Semi-structured patient interviews (n = 34) conducted by a trained qualitative researcher provided the dataset, with traditional qualitative (inductive) analysis by two researchers serving as the gold standard. Two open-source LLMs, Gemma2 and Llama3.1, were used to generate codes, and their performance was assessed based on factors such as chunk size, inductive vs. deductive methods, and prompting approaches. Results showed some alignment between LLM- and researcher-generated codes, with the deductive approach yielding higher and more nuanced insights (Gemma2: n = 723; Llama3.1: n = 1,042) compared to the inductive approach (Gemma2: n = 715; Llama3.1: n = 829). Approximately 45% of the LLM-generated codes provided meaningful context, though 22–39% were duplicative. While LLMs demonstrated efficiency in analyzing large volumes of textual data, nearly half of the codes lacked sufficient context or were repetitive. Our findings showed that although combining traditional qualitative analysis with AI presents a promising avenue, future research should explore how pre-trained LLMs could augment qualitative analysis with higher inter-rater reliability to improve patient-provider communication. There is a need for further research or the development of domain-specific LLMs to improve their utility in qualitative analysis.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
8秒前
幸福海之完成签到,获得积分10
24秒前
盐水菠萝发布了新的文献求助10
28秒前
56秒前
Junex完成签到,获得积分10
56秒前
无限寒珊完成签到,获得积分10
59秒前
欣喜寒烟发布了新的文献求助10
1分钟前
标致的忆梅完成签到,获得积分10
1分钟前
1分钟前
灵剑山发布了新的文献求助10
1分钟前
研友_nxw2xL完成签到,获得积分0
1分钟前
充电宝的应助被科研通管家采纳,获得10
1分钟前
香蕉觅云的应助被科研通管家采纳,获得10
1分钟前
1分钟前
1分钟前
细心慕凝发布了新的文献求助10
1分钟前
欣喜香菇发布了新的文献求助10
1分钟前
Ava的应助被欣喜香菇采纳,获得10
2分钟前
Bowman完成签到,获得积分0
2分钟前
如意紫翠完成签到,获得积分10
2分钟前
细心慕凝完成签到,获得积分10
2分钟前
LHY完成签到,获得积分10
2分钟前
2分钟前
香蕉乐曲完成签到,获得积分10
2分钟前
3分钟前
null的应助被科研通管家采纳,获得10
3分钟前
沉静的愫完成签到,获得积分10
3分钟前
4分钟前
ww完成签到,获得积分10
4分钟前
ww发布了新的文献求助10
4分钟前
4分钟前
adgn发布了新的文献求助10
4分钟前
老实的石头完成签到,获得积分10
4分钟前
4分钟前
个性鹭洋完成签到,获得积分10
5分钟前
丘比特的应助被adgn采纳,获得10
5分钟前
5分钟前
戴肉肉完成签到 ,获得积分10
5分钟前
深情安青的应助被科研通管家采纳,获得10
5分钟前
专注湘完成签到,获得积分10
5分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8173069
求助须知:如何正确求助?哪些是违规求助? 9565519
关于积分的说明 21780383
捐赠科研通 7765085
什么是DOI,文献DOI怎么找? 3431528
关于科研通互助平台的介绍 2555638
邀请新用户注册赠送积分活动 2476668