9 papers · 1 filter
Exploring Sparse Autoencoders in Text-Based Causal Confounding Adjustment
Mian Zhong, Katherine A. Keith, Anjalie Field
In many settings, studying causal questions based on text data requires adjusting for confounding information within texts. Yet there is a tradeoff in constructing text representat…
Op-Fed: Opinion, Stance, and Monetary Policy Annotations on FOMC Transcripts Using Active Learning
Alisa Kanganis, Katherine A. Keith
The U.S. Federal Open Market Committee (FOMC) regularly discusses and sets monetary policy, affecting the borrowing and spending decisions of millions of people. In this work, we r…
Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspects
Katherine A. Keith, Douglas Rice, Brendan O'Connor
Using observed language to understand interpersonal interactions is important in high-stakes decision making. We propose a causal research design for observational (non-experimenta…
Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence
Andrew Halterman, Katherine A. Keith, Sheikh Muhammad Sarwar +1
Automated event extraction in social science applications often requires corpus-level evaluations: for example, aggregating text predictions across metadata and unbiased estimates…
Uncertainty over Uncertainty: Investigating the Assumptions, Annotations, and Text Measurements of Economic Policy Uncertainty
Katherine A. Keith, Christoph Teichmann, Brendan O'Connor +1
Methods and applications are inextricably linked in science, and in particular in the domain of text-as-data. In this paper, we examine one such text-as-data application, an establ…
Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates
Katherine A. Keith, David Jensen, Brendan O'Connor
Many applications of computational social science aim to infer causal conclusions from non-experimental data. Such observational data often contains confounders, variables that inf…