%0 Journal Article
%A Hansen, Stephen
%D 2023
%F discovery:10171178
%I Annual Reviews
%J Annual Review of Economics
%K text as data, topic models, word embeddings, large language models, transformer models, JEL C18, JEL C45, JEL C55
%P 659-688
%T Text Algorithms in Economics
%U https://discovery.ucl.ac.uk/id/eprint/10171178/
%V 15
%X This article provides an overview of the methods used for algorithmic text analysis in economics, with a focus on three key contributions. First, we introduce methods for representing documents as high-dimensional count vectors over vocabulary terms, for representing words as vectors, and for representing word sequences as embedding vectors. Second, we define four core empirical tasks that encompass most text-as-data research in economics and enumerate the various approaches that have been taken so far to accomplish these tasks. Finally, we flag limitations in the current literature, with a focus on the challenge of validating algorithmic output.
%Z © 2023 by the Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).