Bayesian Topic Regression for Causal Inference

Maximilian Ahrens, Julian Ashwin, Jan-Peter Calliess, Vu Nguyen


Abstract
Causal inference using observational text data is becoming increasingly popular in many research areas. This paper presents the Bayesian Topic Regression (BTR) model that uses both text and numerical information to model an outcome variable. It allows estimation of both discrete and continuous treatment effects. Furthermore, it allows for the inclusion of additional numerical confounding factors next to text data. To this end, we combine a supervised Bayesian topic model with a Bayesian regression framework and perform supervised representation learning for the text features jointly with the regression parameter training, respecting the Frisch-Waugh-Lovell theorem. Our paper makes two main contributions. First, we provide a regression framework that allows causal inference in settings when both text and numerical confounders are of relevance. We show with synthetic and semi-synthetic datasets that our joint approach recovers ground truth with lower bias than any benchmark model, when text and numerical features are correlated. Second, experiments on two real-world datasets demonstrate that a joint and supervised learning strategy also yields superior prediction results compared to strategies that estimate regression weights for text and non-text features separately, being even competitive with more complex deep neural networks.
Anthology ID:
2021.emnlp-main.644
Original:
2021.emnlp-main.644v1
Version 2:
2021.emnlp-main.644v2
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8162–8188
Language:
URL:
https://aclanthology.org/2021.emnlp-main.644
DOI:
10.18653/v1/2021.emnlp-main.644
Bibkey:
Cite (ACL):
Maximilian Ahrens, Julian Ashwin, Jan-Peter Calliess, and Vu Nguyen. 2021. Bayesian Topic Regression for Causal Inference. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 8162–8188, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Bayesian Topic Regression for Causal Inference (Ahrens et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.644.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.644.mp4
Code
 maximilianahrens/data