GenAI Powered Dynamic Causal Inference with Unstructured Data

TL;DR

This paper introduces a novel statistical framework leveraging GenAI models for dynamic causal inference with unstructured data like text and video, enabling estimation of causal effects of treatment sequences.

Contribution

It develops a new method combining GenAI representations with neural network-based marginal structural models for causal inference in unstructured data.

Findings

Estimator accurately recovers causal effects in simulations.

Confidence intervals achieve nominal coverage in finite samples.

Application shows treatment effects depend on position within text.

Abstract

A growing number of scholars seek to estimate causal effects of unstructured data such as text, images, and video. However, existing methods typically treat each object as a single, static observation. We develop a statistical framework for dynamic causal inference with unstructured data by leveraging generative artificial intelligence (GenAI) models. Our approach enables researchers to estimate the causal effects of sequences of treatment features, including their positions within text and video. We first extract internal representations of unstructured objects from a GenAI model and then estimate a marginal structural model using a neural network architecture that jointly learns a deconfounder for each treatment feature in the sequence. Our semiparametric inference framework yields valid asymptotic confidence intervals. Simulation studies demonstrate that the proposed estimator recovers the target causal effects and that the confidence intervals achieve nominal coverage in finite samples. We further apply our method to a randomized experiment on the Hong Kong protests, showing that the effect of a treatment feature depends critically on its position within the text.