This repository contains replication data for the article: Griswold, Robbins, and Pollard. (2025). "Stay Tuned: Improving Sentiment Analysis and Stance Detection Using Large Language Models". Political Analysis.


Project data included tweets collected from Twitter between Jan 1st. 2020 and Jan 31st, 2021, for a random subset of general Twitter users and for all members of congress. Tweets were coded for stance concerning candidates in the 2020 US Presidential election. For more details, please see the referenced paper.

This repository also includes stance estimates modeled using several OpenAI Large Language Models. These estimates are included for researchers who are unable to reproduce these results using scripts from the code repository, since these models require proprietary access.

Code related to this project can be found at the following repository: https://github.com/maxgriswold/Stay-Tuned---Improving-Sentiment-Analysis-and-Stance-Detection-Using-Large-Language-Models

Featured Dataverses

In order to use this feature you must have at least one published or linked dataverse.

Publish Dataverse

Are you sure you want to publish your dataverse? Once you do so it must remain published.

Publish Dataverse

This dataverse cannot be published because the dataverse it is in has not been published.

Delete Dataverse

Are you sure you want to delete your dataverse? You cannot undelete this dataverse.

Advanced Search

1 to 10 of 20 Results
api_info.tab
Jun 18, 2025 - Replication Data for: "Stay Tuned - Improving Sentiment Analysis and Stance Detection Using Large Language Models"
Tabular Data - 2.0 KB - 5 Variables, 20 Observations - UNF:6:Y8EyaVm2Z9W1Jct8r4WXWA==
biden_stance_test_public.tab
Jun 18, 2025 - Replication Data for: "Stay Tuned - Improving Sentiment Analysis and Stance Detection Using Large Language Models"
Tabular Data - 71.7 KB - 3 Variables, 375 Observations - UNF:6:FRSOW3K6/01O+ZpjWmbW5A==
Files from Kornraphop Kawintiranon and Lisa Singh. 2021. Knowledge Enhanced Masked Language Model for Stance Detection. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4725–4735, Online. Association for Computational Linguistics. Please cite th...
biden_stance_train_public.tab
Jun 18, 2025 - Replication Data for: "Stay Tuned - Improving Sentiment Analysis and Stance Detection Using Large Language Models"
Tabular Data - 165.6 KB - 3 Variables, 875 Observations - UNF:6:QxjaKzPdquUu+LsvLrL7jQ==
Files from Kornraphop Kawintiranon and Lisa Singh. 2021. Knowledge Enhanced Masked Language Model for Stance Detection. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4725–4735, Online. Association for Computational Linguistics. Please cite th...
cw_house_2022.tab
Jun 18, 2025 - Replication Data for: "Stay Tuned - Improving Sentiment Analysis and Stance Detection Using Large Language Models"
Tabular Data - 19.4 KB - 5 Variables, 442 Observations - UNF:6:ciFPaBVUJmgERhk3iZfirw==
Information on US Congress members in the House of Representatives, crosswalked to Twitter usernames.
cw_senate_2022.tab
Jun 18, 2025 - Replication Data for: "Stay Tuned - Improving Sentiment Analysis and Stance Detection Using Large Language Models"
Tabular Data - 4.6 KB - 5 Variables, 110 Observations - UNF:6:G81+l/EvOW5WyT5IDl/RJQ==
Information on US Congress Senators, crosswalked to Twitter usernames.
politician_tweets_biden.tab
Jun 18, 2025 - Replication Data for: "Stay Tuned - Improving Sentiment Analysis and Stance Detection Using Large Language Models"
Tabular Data - 1.6 MB - 4 Variables, 5876 Observations - UNF:6:2b0lxAxQVlilRtvajwZmFw==
Politician tweets published between 9/20/2020 and 01/20/2021 which contain the word "Biden". Collected by the study team across 2022.
politician_tweets_handcoded.tab
Jun 18, 2025 - Replication Data for: "Stay Tuned - Improving Sentiment Analysis and Stance Detection Using Large Language Models"
Tabular Data - 47.1 KB - 6 Variables, 200 Observations - UNF:6:RFKauqbNHh0wKSPiHaTDLw==
Handcoded tweets for a subset of politicians. Used in supplement to compare handcoded scores to party affiliation and NOMINATE scores.
politician_tweets_trump.tab
Jun 18, 2025 - Replication Data for: "Stay Tuned - Improving Sentiment Analysis and Stance Detection Using Large Language Models"
Tabular Data - 4.3 MB - 4 Variables, 15461 Observations - UNF:6:IcB/SL3kQ5zjgOYYEHomeA==
Politician tweets published between 9/20/2020 and 01/20/2021 which contain the word "Trump". Collected by the study team across 2022.
politician_twitter_profiles.tab
Jun 18, 2025 - Replication Data for: "Stay Tuned - Improving Sentiment Analysis and Stance Detection Using Large Language Models"
Tabular Data - 28.7 KB - 3 Variables, 594 Observations - UNF:6:g2jzmnxrU6T3MSQhx4eLbQ==
Twitter profiles for all politicians analyzed in the study. Used to crosswalk Twitter usernames to party affiliations and NOMINATE scores.
pol_lean.tab
Jun 18, 2025 - Replication Data for: "Stay Tuned - Improving Sentiment Analysis and Stance Detection Using Large Language Models"
Tabular Data - 65.7 KB - 22 Variables, 554 Observations - UNF:6:Z0xsqDv8Qh5Cps2kQsYX8w==
Voteview data for dimension 1 of NOMINATE scores. Please cite "Lewis, Jeffrey B., Keith Poole, Howard Rosenthal, Adam Boche, Aaron Rudkin, and Luke Sonnet (2025). Voteview: Congressional Roll-Call Votes Database. https://voteview.com/" when using this dataset. Underlying data can be found here: https://voteview.com/data
Add Data

Sign up or log in to create a dataverse or add a dataset.

Sign Up Log In
Share Dataverse

Share this dataverse on your favorite social media networks.

Link Dataverse
Reset Modifications

Are you sure you want to reset the selected metadata fields? If you do this, any customizations (hidden, required, optional) you have done will no longer appear.