Multi-scale Hybridized Topic Modeling: A Pipeline for Analyzing Unstructured Text Datasets via Topic Modeling

Authors

Keyi Cheng
Stefan Inzer
Adrian Leung
Xiaoxian Shen
Deanna Needell
Todd Presner
Michael Perlmutter
Michael R. Lindstrom, The University of Texas Rio Grande ValleyFollow
Joyce Chew

Document Type

Article

Publication Date

3-27-2023

Abstract

We propose a multi-scale hybridized topic modeling method to find hidden topics from transcribed interviews more accurately and more efficiently than traditional topic modeling methods. Our multiscale hybridized topic modeling method (MSHTM) approaches data at different scales and performs topic modeling in a hierarchical way utilizing first a classical method, Nonnegative Matrix Factorization, and then a transformer-based method, BERTopic. It harnesses the strengths of both NMF and BERTopic. Our method can help researchers and the public better extract and interpret the interview information. Additionally, it provides insights for new indexing systems based on the topic level. We then deploy our method on real-world interview transcripts and find promising results.

Comments

Original published version available at https://doi.org/10.1137/22S1536832

Recommended Citation

Inzer, Stefan, Keyi Cheng, Adrian Leung, and Xiaoxian Shen. 2023. “Multi-Scale Hybridized Topic Modeling: A Pipeline for Analyzing Unstructured Text Datasets via Topic Modeling.” SIAM Undergraduate Research Online 16. https://doi.org/10.1137/22S1536832

Publication Title

SIAM Undergraduate Research Online 16

DOI

10.1137/22S1536832