How to Make Causal Inferences Using Texts
arXiv:1802.02163
Abstract
New text as data techniques offer a great promise: the ability to inductively discover measures that are useful for testing social science theories of interest from large collections of text. We introduce a conceptual framework for making causal inferences with discovered measures as a treatment or outcome. Our framework enables researchers to discover high-dimensional textual interventions and estimate the ways that observed treatments affect text-based outcomes. We argue that nearly all text-based causal inferences depend upon a latent representation of the text and we provide a framework to learn the latent representation. But estimating this latent representation, we show, creates new risks: we may introduce an identification problem or overfit. To address these risks we describe a split-sample framework and apply it to estimate causal effects from an experiment on immigration attitudes and a study on bureaucratic response. Our work provides a rigorous foundation for text-based causal inferences.
arXiv comment47 pages
References in corpus (2)
Cited by in corpus (11)
- Large-scale Quantitative Evidence of Media Impact on Public Opinion toward China
- Quantifying the Causal Effects of Conversational Tendencies
- Controlled Analyses of Social Biases in Wikipedia Bios
- Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
- A Bayesian approach to modeling topic-metadata relationships
- Everything Has a Cause: Leveraging Causal Inference in Legal Text Analysis
- Generating Synthetic Text Data to Evaluate Causal Inference Methods
- Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspects
- Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP
- Detecting Attackable Sentences in Arguments
- What do writing features tell us about AI papers?