A Multilayer Correlated Topic Model

TL;DR

The paper introduces a multilayer correlated topic model (MCTM) that analyzes how ideas evolve within documents and segments, with applications in document structure understanding and market basket analysis, validated by strong predictive performance.

Contribution

It presents a novel multilayer correlated topic model with a variational EM algorithm, advancing analysis of document structure and customer shopping patterns.

Findings

High predictive accuracy on held-out documents

Effective visualization of document structure

Successful capture of shopping patterns

Abstract

We proposed a novel multilayer correlated topic model (MCTM) to analyze how the main ideas inherit and vary between a document and its different segments, which helps understand an article's structure. The variational expectation-maximization (EM) algorithm was derived to estimate the posterior and parameters in MCTM. We introduced two potential applications of MCTM, including the paragraph-level document analysis and market basket data analysis. The effectiveness of MCTM in understanding the document structure has been verified by the great predictive performance on held-out documents and intuitive visualization. We also showed that MCTM could successfully capture customers' popular shopping patterns in the market basket analysis.