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!

Analyzing Nurse Sentiment in a Dutch Regional Newspaper During the COVID-19 Pandemic: Comparative Content Analysis of GPT-5, Gemini 2.5 Pro, and Human Coding

作者
Bram Van den Berkmortel,Daan Westra,Rachel E. Gifford,Frank Christian Van De Baan
出处
期刊:Journal of Medical Internet Research [JMIR Publications]
卷期号:28: e98374-e98374
标识
DOI:10.2196/98374
摘要

Background: Large language models (LLMs) are increasingly used in qualitative research, but their reliability compared to human analysis, especially on large, non-English datasets, is unclear. Previous studies on older models (like GPT-4) show limitations in nuance and token capacity. Objective: This study compared the qualitative analysis capabilities of OpenAI's GPT-5 and Google's Gemini 2.5 Pro (Gemini) with a human qualitative analysis. The study uses a large dataset of 317 Dutch newspaper articles from January 1, 2020, to December 31, 2023, investigating the sentiment toward nurses during the COVID-19 pandemic. Methods: The study used a 2-phase methodology. First, a thematic comparison was conducted where the human researchers, GPT-5, and Gemini independently generated inductive coding trees from the entire corpus. Second, a comparative test was performed where all 3 coders applied a predefined codebook to a 10% stratified random subsample. The human baseline was validated through double-coding by 2 independent researchers, achieving an acceptable intercoder reliability (α=0.703). The AI analysis was iterative, using model-optimized prompts and an article-by-article approach. Results: Both AI models successfully identified third-order themes (eg, "Health care heroes") consistent with the data. In deductive application, however, both models systematically overcoded compared to the human consensus (181 and 183 codes vs 138), resulting in low intercoder reliability against the human baseline (α=0.487) for GPT-5 and (α=0.507) for Gemini. Conclusions: This study suggests a potential divergence in analytical logic. The observed coding frequencies indicate that LLMs may default to semantic presence (literal frequency), whereas human coders appear to prioritize interpretive significance (contextual weight), leading to systematic overcoding. Consequently, this article argues that LLMs should not be viewed as autonomous researchers but as high-sensitivity filtering instruments requiring human calibration. This study concludes that AI can serve as a valuable assistant for qualitative researchers. Still, it benefits from a rigorous, iterative, and human-in-the-loop approach to manage methodological friction and ensure nuanced, valid 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
丘比特的应助被小麻采纳,获得10
3秒前
9秒前
小蘑菇的应助被灵剑山采纳,获得10
17秒前
安静的卿完成签到,获得积分10
17秒前
wsdow完成签到,获得积分10
25秒前
兴奋的疾完成签到,获得积分10
28秒前
852的应助被ahworld采纳,获得10
32秒前
迷人悒完成签到,获得积分10
45秒前
虚拟的元正完成签到,获得积分10
46秒前
yyy完成签到 ,获得积分10
51秒前
ding的应助被ahworld采纳,获得10
51秒前
fantasy的应助被科研通管家采纳,获得10
56秒前
null的应助被科研通管家采纳,获得10
56秒前
57秒前
1分钟前
淡淡的怜翠完成签到,获得积分10
1分钟前
1分钟前
ni完成签到 ,获得积分10
1分钟前
ahworld发布了新的文献求助10
1分钟前
温不胜的破木吉他完成签到 ,获得积分10
1分钟前
安可完成签到,获得积分20
1分钟前
希望天下0贩的0的应助被安可采纳,获得10
1分钟前
深情豁完成签到,获得积分10
1分钟前
温柔的香岚完成签到,获得积分10
2分钟前
A2QD发布了新的文献求助10
2分钟前
claire完成签到 ,获得积分10
2分钟前
2分钟前
安可发布了新的文献求助10
2分钟前
寒冷的月亮完成签到 ,获得积分10
2分钟前
Nori完成签到 ,获得积分10
2分钟前
土豪的剑身完成签到,获得积分10
2分钟前
脑洞疼的应助被A2QD采纳,获得10
2分钟前
孙菜炖粉条完成签到 ,获得积分10
2分钟前
奔跑的应助被Alice采纳,获得10
2分钟前
独特珩完成签到,获得积分10
2分钟前
明亮的藏鸟完成签到,获得积分10
2分钟前
null的应助被科研通管家采纳,获得10
2分钟前
酷波er的应助被科研通管家采纳,获得10
2分钟前
null的应助被科研通管家采纳,获得10
2分钟前
automan完成签到,获得积分10
2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