Political DEBATE: Efficient Zero-shot and Few-shot Classifiers for Political Text

Social scientists quickly adopted large language models due to their ability to annotate documents without supervised training, an ability known as zero-shot learning. However, due to their compute demands, cost, and often proprietary nature, these models are often at odds with replication and open science standards. This paper introduces the Political DEBATE (DeBERTa Algorithm for Textual Entailment) language models for zero-shot and few-shot classification of political documents. These models are not only as good, or better than, state-of-the art large language models at zero and few-shot classification, but are orders of magnitude more efficient and completely open source. By training the models on a simple random sample of 10-25 documents, they can outperform supervised classifiers trained on hundreds or thousands of documents and state-of-the-art generative models with complex, engineered prompts. Additionally, we release the PolNLI dataset used to train these models -- a corpus of over 200,000 political documents with highly accurate labels across over 800 classification tasks.

What is Sentiment Meant to Mean to Language Models?

Sentiment analysis is one of the most widely used techniques in text analysis. Recent advancements with Large Language Models have made it more accurate and accessible than ever, allowing researchers to classify text with only a plain English prompt. However, "sentiment" entails a wide variety of concepts depending on the domain and tools used. It has been used to mean emotion, opinions, market movements, or simply a general ``good-bad'' dimension. This raises a question: What exactly are language models doing when prompted to label documents by sentiment? This paper first overviews how sentiment is defined across different contexts, highlighting that it is a confounded measurement construct in that it entails multiple variables, such as emotional valence and opinion, without disentangling them. I then test three language models across two data sets with prompts requesting sentiment, valence, and stance classification. I find that sentiment labels most strongly correlate with valence labels. I further find that classification improves when researchers more precisely specify their dimension of interest rather than using the less well-defined concept of sentiment. I conclude by encouraging researchers to move beyond "sentiment" when feasible and use a more precise measurement construct.

Semantic Scaling: Bayesian Ideal Point Estimates with Large Language Models

This paper introduces "Semantic Scaling," a novel method for ideal point estimation from text. I leverage large language models to classify documents based on their expressed stances and extract survey-like data. I then use item response theory to scale subjects from these data. Semantic Scaling significantly improves on existing text-based scaling methods, and allows researchers to explicitly define the ideological dimensions they measure. This represents the first scaling approach that allows such flexibility outside of survey instruments and opens new avenues of inquiry for populations difficult to survey. Additionally, it works with documents of varying length, and produces valid estimates of both mass and elite ideology. I demonstrate that the method can differentiate between policy preferences and in-group/out-group affect. Among the public, Semantic Scaling out-preforms Tweetscores according to human judgement; in Congress, it recaptures the first dimension DW-NOMINATE while allowing for greater flexibility in resolving construct validity challenges.

Stance Detection With Supervised, Zero-Shot, and Few-Shot Applications

Stance detection is the identification of an author's beliefs about a subject from a document. Researchers widely rely on sentiment analysis to accomplish this. However, recent research has show that sentiment analysis is only loosely correlated with stance, if at all. This paper advances methods in text analysis by precisely defining the task of stance detection, providing a generalized framework for the task, and then presenting three distinct approaches for performing stance detection: supervised classification, zero-shot classification with NLI classifiers, and in-context learning. In doing so, I demonstrate how zero-shot and few-shot language classifiers can replace human labelers for a variety of tasks and discuss how their application and limitations differ from supervised classifiers. Finally, I demonstrate an application of zero-shot stance detection by replicating Block Jr et al. (2022).