Multi-label prediction for political text-as-data

Erlich, Aaron, Dantas, Stefano G., Bagozzi, Benjamin E., Berliner, Daniel ORCID: 0000-0002-0285-0215 and Palmer-Rubin, Brian (2022) Multi-label prediction for political text-as-data. Political Analysis, 30 (4). 463 - 480. ISSN 1047-1987

Text (Multitarget_Prediction_final_beforetypesetting) - Accepted Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (436kB)

• Scopus publication
• Author

Abstract

Political scientists increasingly use supervised machine learning to code multiple relevant labels from a single set of texts. The current "best practice"of individually applying supervised machine learning to each label ignores information on inter-label association(s), and is likely to under-perform as a result. We introduce multi-label prediction as a solution to this problem. After reviewing the multi-label prediction framework, we apply it to code multiple features of (i) access to information requests made to the Mexican government and (ii) country-year human rights reports. We find that multi-label prediction outperforms standard supervised learning approaches, even in instances where the correlations among one's multiple labels are low.

Item Type:	Article
Official URL:	https://www.cambridge.org/core/journals/political-...
Additional Information:	© 2021 The Authors
Divisions:	Government
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science J Political Science > JA Political science (General)
Date Deposited:	02 Jul 2021 10:09
Last Modified:	16 Nov 2024 04:33
URI:	http://eprints.lse.ac.uk/id/eprint/110971

Actions (login required)

View Item