Quantitative Tools for Time Series Analysis in Natural Language Processing: A Practitioners Guide

TL;DR

This paper introduces quantitative time series econometric methods, including tests for non-stationarity and structural breaks, to enhance the analysis of topic evolution in natural language processing within social sciences.

Contribution

It provides a comprehensive guide with practical coding advice for applying econometric time series tools to NLP topic analysis, filling a gap in methodological rigor.

Findings

Demonstrates how to detect structural breaks in topic prevalence

Shows the importance of testing for non-stationarity in time series data

Provides a practical example using R software

Abstract

Natural language processing tools have become frequently used in social sciences such as economics, political science, and sociology. Many publications apply topic modeling to elicit latent topics in text corpora and their development over time. Here, most publications rely on visual inspections and draw inference on changes, structural breaks, and developments over time. We suggest using univariate time series econometrics to introduce more quantitative rigor that can strengthen the analyses. In particular, we discuss the econometric topics of non-stationarity as well as structural breaks. This paper serves as a comprehensive practitioners guide to provide researchers in the social and life sciences as well as the humanities with concise advice on how to implement econometric time series methods to thoroughly investigate topic prevalences over time. We provide coding advice for the statistical software R throughout the paper. The application of the discussed tools to a sample dataset completes the analysis.