Codebook Reduction and Saturation: Novel observations on Inductive Thematic Saturation for Large Language Models and initial coding in Thematic Analysis
Abertay University(阿伯泰大学);Yale Medical School(耶鲁医学院)
This paper reflects on the process of performing Thematic Analysis with Large Language Models (LLMs). Specifically, the paper deals with the problem of analytical saturation of initial codes, as produced by LLMs. Thematic Analysis is a well-established qualitative analysis method composed of interlinked phases. A key phase is the initial coding, where the analysts assign labels to discrete components of a dataset. Saturation is a way to measure the validity of a qualitative analysis and relates to the recurrence and repetition of initial codes. In the paper we reflect on how well LLMs achieve analytical saturation and propose also a novel technique to measure Inductive Thematic Saturation (ITS). This novel technique leverages a programming framework called DSPy. The proposed novel approach allows a precise measurement of ITS.
SFT-TA: Supervised Fine-Tuned Agents in Multi-Agent LLMs for Automated Inductive Thematic Analysis
University of Texas at Austin(德克萨斯大学);Vanderbilt University School of Medicine(范德比大学医学院);McCombs School of Business University of Texas at Austin(德克萨斯大学麦康姆商学院)
Automated Healthcare Thematic Analysis using Multi-Agent Large Language Model: Algorithm Development and Evaluation
McWilliams School of Biomedical Informatics, UTHealth Houston(德克萨斯大学休斯顿健康科学中心麦克威廉姆斯生物医学信息学学院);McGovern Medical School, UTHealth Houston(德克萨斯大学休斯顿健康科学中心麦戈文医学院);University of Texas Health Sciences Center Houston(德克萨斯大学休斯顿健康科学中心)
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
Using Large Language Models to Support Thematic Analysis in Empirical Legal Studies
Institute of State and Law of the Czech Academy of Sciences(捷克科学院国家与法律研究所);Institute of Criminal Law and Criminology, Leiden University(莱顿大学刑法与犯罪学研究所);Cyberjustice Laboratory, Université de Montréal(蒙特利尔大学网络司法实验室);School of Computer Science, Carnegie Mellon University(卡内基梅隆大学计算机科学学院)
LLM-TA: An LLM-Enhanced Thematic Analysis Pipeline for Transcripts from Parents of Children with Congenital Heart Disease
School of Information, UT Austin(德克萨斯大学奥斯汀分校信息学院);College of Natural Sciences, UT Austin(德克萨斯大学奥斯汀分校自然科学学院);Graphen, Inc.(格拉芬公司);Vanderbilt University Medical Center(范德堡大学医学中心);Pediatric Heart Institute at Monroe Carell Jr. Children’s Hospital at Vanderbilt(范德堡大学门罗·卡雷尔 Jr.儿童医院儿科心脏研究所);Texas Center for Pediatric and Congenital Heart Disease(德克萨斯儿科与先天性心脏病中心);Dell Medical School, UT Austin(德克萨斯大学奥斯汀分校戴尔医学院)
Automated Thematic Analyses Using LLMs: Xylazine Wound Management Social Media Chatter Use Case
Emory University(埃默里大学);Wheeler High School(惠勒高中);Rutgers New Jersey Medical School(罗格斯新泽西医学院);Perelman School of Medicine, University of Pennsylvania(宾夕法尼亚大学佩雷尔曼医学院)
Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives
Department of Computer Science, Columbia University(哥伦比亚大学计算机科学系);Department of Applied Physics and Applied Mathematics, Columbia University(哥伦比亚大学应用物理与应用数学系);Department of Psychology, Northwestern University(西北大学心理学系)