FactorFlow: A Visual Analytics Workspace with Large Language Model-Assisted Interpretation for Factor Analysis
Abstract
In exploratory factor analysis (EFA), one aims to describe latent variables by constructing a factor model based on the relationships among manifest variables. For a model to be useful, it is not enough that it is grounded on data; it must also be meaningful. Hence, in practice, one attempts to interpret different factor models to identify a meaningful, coherent, and theoretically defensible latent structure. Doing so, however, is not straightforward, as it is subjective and requires tracking extensive information. Thus, we introduce FactorFlow, a system designed to help researchers perform EFA more effectively. With an interactive dashboard that supports comprehensively visualizing up to two models simultaneously and large language model integration that enables the generation of automated model interpretations written in natural language, FactorFlow substantially aids the crucial step of model interpretation, all the while supporting the end-to-end workflow. Indeed, our usability survey evidences the effectiveness of FactorFlow.
Related
- Application of spectroscopic and multispectral imaging technologies on the assessment of ready-to-eat pineapple quality: A performance evaluation study of machine learning models generated from two commercial data analytics tools
- The role of big data analytics in financial fraud detection: A systematic literature review
- Supply Chain Analytics: A Data-Driven Approach
- Mapping Academic Sports Analytics: A Content Analysis of JQAS and JSA
- Addressing Data Engineering Challenges in the Cold-Chain Sector to Reduce its Environmental Impact Through Analytics
BibTeX
@misc{tuazon2026factorflow,
title = {{FactorFlow: A Visual Analytics Workspace with Large Language Model-Assisted Interpretation for Factor Analysis}},
author = {Justin Philip Tuazon and Joemari Olea and Richelle Ann Juayong},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.13585},
eprint = {2608.13585},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.13585},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - FactorFlow: A Visual Analytics Workspace with Large Language Model-Assisted Interpretation for Factor Analysis
AU - Justin Philip Tuazon
AU - Joemari Olea
AU - Richelle Ann Juayong
PY - 2026
DA - 2026/09/10
PB - arXiv
DO - 10.48550/arxiv.2608.13585
UR - https://arxiv.org/abs/2608.13585
AB - In exploratory factor analysis (EFA), one aims to describe latent variables by constructing a factor model based on the relationships among manifest variables. For a model to be useful, it is not enough that it is grounded on data; it must also be meaningful. Hence, in practice, one attempts to interpret different factor models to identify a meaningful, coherent, and theoretically defensible latent structure. Doing so, however, is not straightforward, as it is subjective and requires tracking extensive information. Thus, we introduce FactorFlow, a system designed to help researchers perform EFA more effectively. With an interactive dashboard that supports comprehensively visualizing up to two models simultaneously and large language model integration that enables the generation of automated model interpretations written in natural language, FactorFlow substantially aids the crucial step of model interpretation, all the while supporting the end-to-end workflow. Indeed, our usability survey evidences the effectiveness of FactorFlow.
ER -