Econometrics Meets Sentiment: An Overview of Methodology and Applications

Abstract

The advent of massive amounts of textual, audio, and visual data has spurred the development of econometric methodology to transform qualitative sentiment data into quantitative sentiment variables, and to use those variables in an econometric analysis of the relationships between sentiment and other variables. We survey this emerging research field and refer to it as sentometrics, which is a portmanteau of sentiment and econometrics. We provide a synthesis of the relevant methodological approaches, illustrate with empirical results, and discuss useful software.

The Economic Policy Uncertainty Index for Flanders, Wallonia and Belgium

“…Text-based indices have the advantage of being flexible, timely, and are able to uncover latent variables. For an overview of the different steps in creating and researching the added value of textual indices, we refer to the survey of Algaba et al (2020).…”

A New Measure of 19th Century US Suicides

“…Using text and especially newspapers as data is a recent development. Yet, already an entire literature using text as data exists (Algaba et al, 2020;Baker et al, 2016;Currie et al, 2020;Gentzkow et al, 2011Gentzkow et al, , 2014Gentzkow et al, , 2015Gutmann et al, 2018;Marquardt, 2020). A prominent example is the work by Baker et al (2016).…”

Sentiment Analysis of Financial News: Mechanics and Statistics

“…Example 1 Targets (e.g., a company name or stock ticker) can be identified by keyword matching or name entity recognition techniques (check out the Stanford NER software. 1 ) Alternatively, some news providers like Dow Jones Newswires include labels in their xml files indicating the company that the news is about.…”

“…A few selected examples from the vast amount of published research on the subject of forecasting and portfolio management with sentiment data are [3,4,6,21,29,44,45,49]. For a more extensive treatment of the building blocks for producing models based on textual data, see [1] and the tutorial for the sentometrics package in [2].…”