CollabCoder: A Lower-barrier, Rigorous Workflow for Inductive Collaborative Qualitative Analysis with Large Language Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Gao, Jie, Guo, Yuchen, Lim, Gionnieve, Zhang, Tianqin, Zhang, Zheng, Li, Toby Jia-Jun, Perrault, Simon Tangi
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913201460871168
author Gao, Jie
Guo, Yuchen
Lim, Gionnieve
Zhang, Tianqin
Zhang, Zheng
Li, Toby Jia-Jun
Perrault, Simon Tangi
author_facet Gao, Jie
Guo, Yuchen
Lim, Gionnieve
Zhang, Tianqin
Zhang, Zheng
Li, Toby Jia-Jun
Perrault, Simon Tangi
contents Collaborative Qualitative Analysis (CQA) can enhance qualitative analysis rigor and depth by incorporating varied viewpoints. Nevertheless, ensuring a rigorous CQA procedure itself can be both demanding and costly. To lower this bar, we take a theoretical perspective to design the CollabCoder workflow, that integrates Large Language Models (LLMs) into key inductive CQA stages: independent open coding, iterative discussions, and final codebook creation. In the open coding phase, CollabCoder offers AI-generated code suggestions and records decision-making data. During discussions, it promotes mutual understanding by sharing this data within the coding team and using quantitative metrics to identify coding (dis)agreements, aiding in consensus-building. In the code grouping stage, CollabCoder provides primary code group suggestions, lightening the cognitive load of finalizing the codebook. A 16-user evaluation confirmed the effectiveness of CollabCoder, demonstrating its advantages over existing software and providing empirical insights into the role of LLMs in the CQA practice.
format Preprint
id arxiv_https___arxiv_org_abs_2304_07366
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CollabCoder: A Lower-barrier, Rigorous Workflow for Inductive Collaborative Qualitative Analysis with Large Language Models
Gao, Jie
Guo, Yuchen
Lim, Gionnieve
Zhang, Tianqin
Zhang, Zheng
Li, Toby Jia-Jun
Perrault, Simon Tangi
Human-Computer Interaction
Collaborative Qualitative Analysis (CQA) can enhance qualitative analysis rigor and depth by incorporating varied viewpoints. Nevertheless, ensuring a rigorous CQA procedure itself can be both demanding and costly. To lower this bar, we take a theoretical perspective to design the CollabCoder workflow, that integrates Large Language Models (LLMs) into key inductive CQA stages: independent open coding, iterative discussions, and final codebook creation. In the open coding phase, CollabCoder offers AI-generated code suggestions and records decision-making data. During discussions, it promotes mutual understanding by sharing this data within the coding team and using quantitative metrics to identify coding (dis)agreements, aiding in consensus-building. In the code grouping stage, CollabCoder provides primary code group suggestions, lightening the cognitive load of finalizing the codebook. A 16-user evaluation confirmed the effectiveness of CollabCoder, demonstrating its advantages over existing software and providing empirical insights into the role of LLMs in the CQA practice.
title CollabCoder: A Lower-barrier, Rigorous Workflow for Inductive Collaborative Qualitative Analysis with Large Language Models
topic Human-Computer Interaction
url https://arxiv.org/abs/2304.07366