Corpus ID: 3613569

How to Make Causal Inferences Using Texts

@article{Egami2018HowTM,
  title={How to Make Causal Inferences Using Texts},
  author={Naoki Egami and Christian Fong and Justin Grimmer and Margaret E. Roberts and Brandon M Stewart},
  journal={ArXiv},
  year={2018},
  volume={abs/1802.02163}
}
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… Expand
Improving Causal Inference with Text as Data in Empirical IS Research: A Machine Learning Approach
TLDR
It is shown that transforming text into quantitative data makes the treatment effect estimation more accurate, which implies that the positive effect of ‘Elite’ badge was overestimated without text information. Expand
Using Text Embeddings for Causal Inference
TLDR
The proposed method adapts deep language models to learn low-dimensional embeddings from text that predict these values well and suffice for causal adjustment; it empirically on semi-simulated and real data on paper acceptance and forum post popularity. Expand
Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates
TLDR
This review is the first to gather and categorize examples of potential confounders from observed text and provide a guide to data-processing and evaluation decisions. Expand
Generating Synthetic Text Data to Evaluate Causal Inference Methods
TLDR
This work develops a framework for adapting existing generation models to produce synthetic text datasets with known causal effects and uses this framework to perform an empirical comparison of four recently-proposed methods for estimating causal effects from text data. Expand
Text as Causal Mediators: Research Design for Causal Estimates of Differential Treatment of Social Groups via Language Aspects
Using observed language to understand interpersonal interactions is important in highstakes decision making. We propose a causal research design for observational (nonexperimental) data to estimateExpand
Challenges of Using Text Classifiers for Causal Inference
TLDR
It is demonstrated how to conduct causal analyses using text classifiers on simulated and Yelp data, and the opportunities and challenges of future work that uses text data in causal inference are discussed. Expand
Adjusting for Confounding with Text Matching
TLDR
A method of text matching, topical inverse regression matching, that allows the analyst to match both on the topical content of confounding documents and the probability that each of these documents is treated is proposed. Expand
Uncovering Latent Biases in Text: Method and Application to Peer Review
TLDR
A novel framework to quantify bias in text caused by the visibility of subgroup membership indicators and shows evidence of biases in the review ratings that serves as "ground truth", and shows that the proposed framework accurately detects these biases from the review text without having access to the review Ratings. Expand
Essays on the Applications of Machine Learning and Causal Inference in American Politics
Political science as a field prioritizes causal statements: the effects of governmental policies on societal outcomes, the effects of individual treatments on individual behaviors. Underlying theseExpand
Quantifying the Causal Effects of Conversational Tendencies
  • Justine Zhang
  • Computer Science, Psychology
  • Proc. ACM Hum. Comput. Interact.
  • 2020
TLDR
This work formally describes the problem of drawing causal links between conversational behaviors and outcomes, and focuses on the task of determining a particular type of policy for a text-based crisis counseling platform: how best to allocate counselors based on their behavioral tendencies exhibited in their past conversations. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 81 REFERENCES
Discovery of Treatments from Text Corpora
TLDR
A new experimental design and statistical model is introduced to simultaneously discover treatments in a corpora and estimate causal effects for these discovered treatments and the effects of these interventions in a test set of new texts and survey respondents. Expand
A Model of Text for Experimentation in the Social Sciences
ABSTRACT Statistical models of text have become increasingly popular in statistics and computer science as a method of exploring large document collections. Social scientists often want to moveExpand
Causal Inference in Conjoint Analysis: Understanding Multidimensional Choices via Stated Preference Experiments
Survey experiments are a core tool for causal inference. Yet, the design of classical survey experiments prevents them from identifying which components of a multidimensional treatment areExpand
Causal inference for ordinal outcomes
Many outcomes of interest in the social and health sciences, as well as in modern applications in computational social science and experimentation on social media platforms, are ordinal and do notExpand
Text Preprocessing For Unsupervised Learning: Why It Matters, When It Misleads, And What To Do About It
TLDR
To aid researchers working in unsupervised settings, a statistical procedure and software is introduced that examines the sensitivity of findings under alternate preprocessing regimes and provides a characterization of the variability changes in preprocessing choices may induce when analyzing a particular dataset. Expand
Using Split Samples to Improve Inference on Causal Effects
TLDR
Simulations indicate that, under empirically relevant settings, the proposed method delivers more power than a PAP but is better suited for exploratory analyses where there is significant uncertainty about the outcomes of interest. Expand
Extracting Policy Positions from Political Texts Using Words as Data
We present a new way of extracting policy positions from political texts that treats texts not as discourses to be understood and interpreted but rather, as data in the form of words. We compare thisExpand
What Can We Learn from Predictive Modeling?
TLDR
The central benefits of predictive modeling are reviewed from a perspective uncommon in the existing literature: it is focused on how predictive modeling can be used to complement and augment standard associational analyses. Expand
Causal Inference
  • J. Pearl
  • Computer Science
  • NIPS Causality: Objectives and Assessment
  • 2010
TLDR
The theory unifies the graphical, potential-outcome, decision analytical, and structural equation approaches to causation, and provides both a mathematical foundation and a friendly calculus for the analysis of causes and counterfactuals. Expand
Causal Inference in Latent Class Analysis
TLDR
2 propensity score techniques, matching and inverse propensity weighting, are demonstrated for conducting causal inference in LCA, and the different causal questions that can be addressed are carefully delineated. Expand
...
1
2
3
4
5
...