Improving the TENOR of Labeling: Re-evaluating Topic Models for Content Analysis

Published

March 23, 2024

Author(s)

Zongxia Li, Andrew Mao, Jordan Boyd-Graber, Daniel Stephens, Emily Walpole, Alden A. Dima, Juan Fung

Abstract

Topic models are a popular tool for understanding text collections, but their evaluation has been a point of contention. Automated evaluation metrics such as coherence are often used, however, their validity has been questioned for neural topic models (NTMs) and can overlook a model's benefits in real-world applications. To this end, we conduct the first evaluation of neural, supervised and classical topic models in an interactive task-based setting. We combine topic models with a classifier and test their ability to help humans conduct content analysis and document annotation. From simulated, real user and expert pilot studies, the Contextual Neural Topic Model does the best on cluster evaluation metrics and human evaluations; however, LDA is competitive with two other NTMs under our simulated experiment and user study results, contrary to what coherence scores suggest. We show that current automated metrics do not provide a complete picture of topic modeling capabilities, but the right choice of NTMs can be better than classical models on practical tasks.

Proceedings Title

Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

Conference Dates

March 17-22, 2024

Conference Location

St. Julian's, MT

Conference Title

The 18th Conference of the European Chapter of the Association for Computational Linguistics

Pub Type

Conferences

Download Paper

Local Download

Keywords

topic models, active learning, human-in-the-loop, document labeling, annotation, natural language processing, technical language processing

Citation

Li, Z. , Mao, A. , Boyd-Graber, J. , Stephens, D. , Walpole, E. , Dima, A. and Fung, J. (2024), Improving the TENOR of Labeling: Re-evaluating Topic Models for Content Analysis, Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), St. Julian's, MT, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=956761 (Accessed November 21, 2024)