CFTM: Continuous time fractional topic model

TL;DR

The paper introduces cFTM, a novel dynamic topic model utilizing fractional Brownian motion to capture long-term dependencies and roughness in topic evolution over time, with theoretical validation and empirical testing on economic news.

Contribution

It presents the first continuous-time fractional topic model that incorporates fBm for capturing long-term dependencies in topic dynamics, with proven estimation efficiency.

Findings

Successfully captures long-term dependency and roughness in topics.

Estimates parameters efficiently comparable to LDA.

Empirically validates model on economic news articles.

Abstract

In this paper, we propose the Continuous Time Fractional Topic Model (cFTM), a new method for dynamic topic modeling. This approach incorporates fractional Brownian motion~(fBm) to effectively identify positive or negative correlations in topic and word distribution over time, revealing long-term dependency or roughness. Our theoretical analysis shows that the cFTM can capture these long-term dependency or roughness in both topic and word distributions, mirroring the main characteristics of fBm. Moreover, we prove that the parameter estimation process for the cFTM is on par with that of LDA, traditional topic models. To demonstrate the cFTM's property, we conduct empirical study using economic news articles. The results from these tests support the model's ability to identify and track long-term dependency or roughness in topics over time.