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

TL;DR

This paper evaluates neural, supervised, and classical topic models in an interactive content analysis setting, revealing that automated metrics like coherence are insufficient and that neural models can outperform classical ones in practical tasks.

Contribution

It provides the first comprehensive evaluation of different topic models in a human-centered, interactive context, highlighting the limitations of automated metrics and the practical advantages of neural models.

Findings

Contextual Neural Topic Model performs best on human evaluations.

LDA remains competitive with neural models in simulated and user studies.

Automated coherence scores do not fully capture model effectiveness in real-world tasks.

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 models 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 task.