A Query-Driven Topic Model

TL;DR

This paper introduces a query-driven topic model that enables users to find relevant topics based on simple queries, especially effective for low-occurrence queries, improving over traditional and neural models.

Contribution

It presents a novel topic modeling approach that incorporates user queries directly, reducing reliance on domain expertise and enhancing detection of low-frequency relevant topics.

Findings

Outperforms classical topic models in relevance and accuracy.

Effective in identifying low-occurrence, query-related topics.

Demonstrates superiority over neural topic models in experiments.

Abstract

Topic modeling is an unsupervised method for revealing the hidden semantic structure of a corpus. It has been increasingly widely adopted as a tool in the social sciences, including political science, digital humanities and sociological research in general. One desirable property of topic models is to allow users to find topics describing a specific aspect of the corpus. A possible solution is to incorporate domain-specific knowledge into topic modeling, but this requires a specification from domain experts. We propose a novel query-driven topic model that allows users to specify a simple query in words or phrases and return query-related topics, thus avoiding tedious work from domain experts. Our proposed approach is particularly attractive when the user-specified query has a low occurrence in a text corpus, making it difficult for traditional topic models built on word cooccurrence patterns to identify relevant topics. Experimental results demonstrate the effectiveness of our model in comparison with both classical topic models and neural topic models.