Skip to main content

An embedding model for estimating legislative preferences from the frequency and sentiment of tweets

Publication ,  Conference
Spell, GP; Hillygus, DS; Guay, B; Carin, L
Published in: EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
January 1, 2020

Legislator preferences are typically represented as measures of general ideology estimated from roll call votes on legislation, potentially masking important nuances in legislators' political attitudes. In this paper we introduce a method of measuring more specific legislator attitudes using an alternative expression of preferences: tweeting. Specifically, we present an embedding-based model for predicting the frequency and sentiment of legislator tweets. To illustrate our method, we model legislators' attitudes towards President Donald Trump as vector embeddings that interact with embeddings for Trump himself constructed using a neural network from the text of his daily tweets. We demonstrate the predictive performance of our model on tweets authored by members of the U.S. House and Senate related to the president from November 2016 to February 2018. We further assess the quality of our learned representations for legislators by comparing to traditional measures of legislator preferences.

Duke Scholars

Published In

EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

DOI

Publication Date

January 1, 2020

Start / End Page

627 / 641
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Spell, G. P., Hillygus, D. S., Guay, B., & Carin, L. (2020). An embedding model for estimating legislative preferences from the frequency and sentiment of tweets. In EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 627–641). https://doi.org/10.18653/v1/2020.emnlp-main.46
Spell, G. P., D. S. Hillygus, B. Guay, and L. Carin. “An embedding model for estimating legislative preferences from the frequency and sentiment of tweets.” In EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, 627–41, 2020. https://doi.org/10.18653/v1/2020.emnlp-main.46.
Spell GP, Hillygus DS, Guay B, Carin L. An embedding model for estimating legislative preferences from the frequency and sentiment of tweets. In: EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. 2020. p. 627–41.
Spell, G. P., et al. “An embedding model for estimating legislative preferences from the frequency and sentiment of tweets.” EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, 2020, pp. 627–41. Scopus, doi:10.18653/v1/2020.emnlp-main.46.
Spell GP, Hillygus DS, Guay B, Carin L. An embedding model for estimating legislative preferences from the frequency and sentiment of tweets. EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. 2020. p. 627–641.

Published In

EMNLP 2020 - 2020 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

DOI

Publication Date

January 1, 2020

Start / End Page

627 / 641