Stance Detection: A Practical Guide to Classifying Political Beliefs in Text
It provides a practical guide for researchers and practitioners in text analysis, but it is incremental as it synthesizes and compares existing methods without introducing new techniques.
This paper tackles the problem of stance detection in text by defining it precisely and presenting three approaches: supervised classification, natural language inference, and in-context learning with generative language models, demonstrating that newer methods can replicate supervised classifiers.
Stance detection is identifying expressed beliefs in a document. While researchers widely use sentiment analysis for this, recent research demonstrates that sentiment and stance are distinct. This paper advances text analysis methods by precisely defining stance detection and presenting three distinct approaches: supervised classification, natural language inference, and in-context learning with generative language models. I discuss how document context and trade-offs between resources and workload should inform your methods. For all three approaches I provide guidance on application and validation techniques, as well as coding tutorials for implementation. Finally, I demonstrate how newer classification approaches can replicate supervised classifiers.