scotus_tweets

This dataset contains 945 tweets referencing the US Supreme Court.
Roughly half were collected on June 4, 2018 following the Masterpiece Cakeshop
ruling, and the other half were collected on July 9, 2020 following the
Court's concurrently released opinions in Trump v. Mazars and Trump v. Vance.
Each tweet includes three independent human-coded sentiment scores (-1 to +1).

datasets

Format and submit few-shot prompts to OpenAI's Large Language Models (LLMs). Designed to be particularly useful for text classification problems in the social sciences. Methods are described in Ornstein, Blasingame, and Truscott (2024) <https://joeornstein.github.io/publications/ornstein-blasingame-truscott.pdf>.

Joe Ornstein

promptr

Format and Complete Few-Shot LLM Prompts

scotus_tweets function

A data frame with 945 rows and 5 columns:<dl>
<dt>tweet_id</dt>
<dd>A unique ID</dd><dt>text</dt>
<dd>The text of the tweet</dd><dt>case</dt>
<dd>An identifier denoting which Supreme Court ruling the tweet was collected after.</dd><dt>expert1, expert2, expert3</dt>
<dd>Hand-coded sentiment score (-1 = negative, 0 = neutral, 1 = positive)</dd>
</dl>

Format

Tweets About The Supreme Court of the United States — scotus_tweets

A data frame with 945 rows and 5 columns:<dl>
<dt>tweet_id</dt>
<dd>A unique ID</dd>

<dt>text</dt>
<dd>The text of the tweet</dd>

<dt>case</dt>
<dd>An identifier denoting which Supreme Court ruling the tweet was collected after.</dd>

<dt>expert1, expert2, expert3</dt>
<dd>Hand-coded sentiment score (-1 = negative, 0 = neutral, 1 = positive)</dd>


</dl>

scotus_tweets: Tweets About The Supreme Court of the United States

Description

Usage

Arguments

Format

Details

References