A Neural Topic Method Using a Large-Language-Model-in-the-Loop for Business Research

TL;DR

This paper introduces LX Topic, a neural topic modeling approach that leverages large language models to produce interpretable, stable, and high-quality topics from unstructured business text data, improving measurement and analysis.

Contribution

It presents LX Topic, a novel neural topic method integrating large language models with alignment and confidence mechanisms for better interpretability and stability in business research applications.

Findings

Achieves highest topic quality on Amazon and Yelp datasets.

Maintains clustering and classification performance.

Provides a reproducible, web-based system for business text analysis.

Abstract

The growing use of unstructured text in business research makes topic modeling a central tool for constructing explanatory variables from reviews, social media, and open-ended survey responses, yet existing approaches function poorly as measurement instruments. Prior work shows that textual content predicts outcomes such as sales, satisfaction, and firm performance, but probabilistic models often generate conceptually diffuse topics, neural topic models are difficult to interpret in theory-driven settings, and large language model approaches lack standardization, stability, and alignment with document-level representations. We introduce LX Topic, a neural topic method that conceptualizes topics as latent linguistic constructs and produces calibrated document-level topic proportions for empirical analysis. LX Topic builds on FASTopic to ensure strong document representativeness and integrates large language model refinement at the topic-word level using alignment and confidence-weighting mechanisms that enhance semantic coherence without distorting document-topic distributions. Evaluations on large-scale Amazon and Yelp review datasets demonstrate that LX Topic achieves the highest overall topic quality relative to leading models while preserving clustering and classification performance. By unifying topic discovery, refinement, and standardized output in a web-based system, LX Topic establishes topic modeling as a reproducible, interpretable, and measurement-oriented instrument for marketing research and practice.