Text and Causal Inference: A Review of Using Text to Remove Confounding from Causal Estimates

ACL, pp. 5332-5344, 2020.

Cited by: 2|Bibtex|Views17|Links
EI
Keywords:
average treatment effectaverage treatment effect on the controlsample average treatment effectLinguistic Inquiry and Word Countstructural causal modelsMore(17+)
Weibo:
We encourage researchers to evaluate with constructed observational studies or semi-synthetic datasets, measuring latent confounders from text increases the difficulty of creating realistic datasets that can be used for empirical evaluation of causal methods

Abstract:

Many applications of computational social science aim to infer causal conclusions from non-experimental data. Such observational data often contains confounders, variables that influence both potential causes and potential effects. Unmeasured or latent confounders can bias causal estimates, and this has motivated interest in measuring p...More

Code:

Data:

0
Introduction
  • In contrast to descriptive or predictive tasks, causal inference aims to understand how intervening on one variable affects another variable (Holland, 1986; Pearl, 2000; Morgan and Winship, 2015; Imbens and Rubin, 2015; Hernn and Robins, 2020).
  • Many applied researchers aim to estimate the size of a specific causal effect, the effect of a single treatment variable on an outcome variable.
  • Consider estimating the size of the causal effect of smoking on life expectancy.
  • Occupation is a potential confounder that may influence both the propensity to smoke and life expectancy.
  • Estimating the effect of treatment on outcome without accounting for this confounding could result in strongly biased estimates and invalid causal conclusions
Highlights
  • In contrast to descriptive or predictive tasks, causal inference aims to understand how intervening on one variable affects another variable (Holland, 1986; Pearl, 2000; Morgan and Winship, 2015; Imbens and Rubin, 2015; Hernn and Robins, 2020)
  • For natural language processing researchers working with causal inference, we summarize some of the most-used causal estimators that condition on confounders: matching, propensity score weighting, regression adjustment, doubly-robust methods, and causally-driven representation learning (§5)
  • We provide an overview of methods used by applications in this review that approximate such conditioning, leading to unbiased estimates of treatment effect; we acknowledge this is not an exhaustive list of methods and direct readers to more extensive guides (Morgan and Winship, 2015; Athey et al, 2017)
  • We encourage researchers to evaluate with constructed observational studies or semi-synthetic datasets, measuring latent confounders from text increases the difficulty of creating realistic datasets that can be used for empirical evaluation of causal methods
  • While text data ought to be as useful for measurement and inference as “traditional” lowdimensional social-scientific variables, combining natural language processing with causal inference methods requires tackling major open research questions
  • Along with the others presented in this paper, would be a major advance for natural language processing as a social science methodology
Results
  • Evaluation of causal methods

    Because the true causal effects in real-world causal inference are typically unknown, causal evaluation is a difficult and open research question.
  • Constructed observational studies collect data from both randomized and non-randomized experiments with similar participants and settings
  • Evaluations of this kind include job training programs in economics (LaLonde, 1986; Glynn and Kashin, 2013), advertisement marketing campaigns (Gordon et al, 2019), and education (Shadish et al, 2008).
  • Shadish et al (2008) randomly assign participants to a randomized treatment and non-randomized treatment
  • They compare causal effect estimates from the randomized study with observational estimates that condition on confounders from participant surveys
Conclusion
  • Discussion and Conclusion

    Computational social science is an exciting, rapidly expanding discipline.
  • The authors caution against using all available text in causal adjustment methods without any human validation or supervision, since one cannot diagnose any potential errors.
  • Solving these open problems, along with the others presented in this paper, would be a major advance for NLP as a social science methodology
Summary
  • Introduction:

    In contrast to descriptive or predictive tasks, causal inference aims to understand how intervening on one variable affects another variable (Holland, 1986; Pearl, 2000; Morgan and Winship, 2015; Imbens and Rubin, 2015; Hernn and Robins, 2020).
  • Many applied researchers aim to estimate the size of a specific causal effect, the effect of a single treatment variable on an outcome variable.
  • Consider estimating the size of the causal effect of smoking on life expectancy.
  • Occupation is a potential confounder that may influence both the propensity to smoke and life expectancy.
  • Estimating the effect of treatment on outcome without accounting for this confounding could result in strongly biased estimates and invalid causal conclusions
  • Results:

    Evaluation of causal methods

    Because the true causal effects in real-world causal inference are typically unknown, causal evaluation is a difficult and open research question.
  • Constructed observational studies collect data from both randomized and non-randomized experiments with similar participants and settings
  • Evaluations of this kind include job training programs in economics (LaLonde, 1986; Glynn and Kashin, 2013), advertisement marketing campaigns (Gordon et al, 2019), and education (Shadish et al, 2008).
  • Shadish et al (2008) randomly assign participants to a randomized treatment and non-randomized treatment
  • They compare causal effect estimates from the randomized study with observational estimates that condition on confounders from participant surveys
  • Conclusion:

    Discussion and Conclusion

    Computational social science is an exciting, rapidly expanding discipline.
  • The authors caution against using all available text in causal adjustment methods without any human validation or supervision, since one cannot diagnose any potential errors.
  • Solving these open problems, along with the others presented in this paper, would be a major advance for NLP as a social science methodology
Tables
  • Table1: Example applications that infer the causal effects of treatment on outcome by measuring confounders (unobserved) from text data (observed). In doing so, these applications choose a representation of text (text rep.) and a method to adjust for confounding
Download tables as Excel
Reference
  • Alberto Abadie, David Drukker, Jane Leber Herr, and Guido W Imbens. 2004. Implementing matching estimators for average treatment effects in stata. The Stata Journal, 4(3):290–311.
    Google ScholarLocate open access versionFindings
  • Maria Antoniak and David Mimno. 2018. Evaluating the stability of embedding-based word similarities. Transactions of the Association for Computational Linguistics, 6:107–119.
    Google ScholarLocate open access versionFindings
  • Sanjeev Arora, Yingyu Liang, and Tengyu Ma. 2017. A simple but tough-to-beat baseline for sentence embeddings. In ICLR.
    Google ScholarFindings
  • Susan Athey, Guido Imbens, Thai Pham, and Stefan Wager. 2017. Estimating average treatment effects: Supplementary analyses and remaining challenges. American Economic Review, 107(5):278–81.
    Google ScholarLocate open access versionFindings
  • Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Kiros, Hongyuan Mei, and Dipendra Misra. 2018. Proceedings of the Third Workshop on Representation Learning for NLP. In Proceedings of The Third Workshop on Representation Learning for NLP.
    Google ScholarLocate open access versionFindings
  • Isabelle Augenstein, Spandana Gella, Sebastian Ruder, Katharina Kann, Burcu Can, Johannes Welbl, Alexis Conneau, Xiang Ren, and Marek Rei. 2019. Proceedings of the 4th Workshop on Representation Learning for NLP. In Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019).
    Google ScholarLocate open access versionFindings
  • Ananth Balashankar, Sunandan Chakraborty, Samuel Fraiberger, and Lakshminarayanan Subramanian. 2019. Identifying predictive causal factors from news streams. In Empirical Methods in Natural Langugage Processing.
    Google ScholarLocate open access versionFindings
  • David M Blei, Andrew Y Ng, and Michael I Jordan. 2003. Latent Dirichlet Allocation. Journal of Machine Learning Research, 3(Jan):993–1022.
    Google ScholarLocate open access versionFindings
  • Su Lin Blodgett and Brendan O’Connor. 2017. Racial disparity in natural language processing: A case study of social media african-american english. In Fairness, Accountability, and Transparency in Machine Learning (FAT/ML) Workshop, KDD.
    Google ScholarLocate open access versionFindings
  • Phil Blunsom, Antoine Bordes, Kyunghyun Cho, Shay Cohen, Chris Dyer, Edward Grefenstette, Karl Moritz Hermann, Laura Rimell, Jason Weston, and Scott Yih. 2017. Proceedings of the 2nd Workshop on Representation Learning for NLP. In Proceedings of the 2nd Workshop on Representation Learning for NLP.
    Google ScholarLocate open access versionFindings
  • Phil Blunsom, Kyunghyun Cho, Shay Cohen, Edward Grefenstette, Karl Moritz Hermann, Laura Rimell, Jason Weston, and Scott Wen-tau Yih. 2016. Proceedings of the 1st Workshop on Representation Learning for NLP. In Proceedings of the 1st Workshop on Representation Learning for NLP.
    Google ScholarLocate open access versionFindings
  • Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. Transactions of the Association for Computational Linguistics, 5:135–146.
    Google ScholarLocate open access versionFindings
  • Jordan Boyd-Graber, David Mimno, and David Newman. 2014. Care and feeding of topic models: Problems, diagnostics, and improvements. Handbook of Mixed Membership Models and Their Applications, 225255.
    Google ScholarLocate open access versionFindings
  • John P Buonaccorsi. 2010. Measurement Error: Models, Methods, and Applications. CRC Press.
    Google ScholarFindings
  • Marco Caliendo and Sabine Kopeinig. 2008. Some practical guidance for the implementation of propensity score matching. Journal of Economic Surveys, 22(1):31–72.
    Google ScholarLocate open access versionFindings
  • Dallas Card and Noah A Smith. 2018. The importance of calibration for estimating proportions from annotations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Raymond J Carroll, David Ruppert, Leonard A Stefanski, and Ciprian M Crainiceanu. 2006. Measurement Error in Nonlinear Models: a Modern Perspective. CRC Press.
    Google ScholarFindings
  • Daniel Cer, Mona Diab, Eneko Agirre, Inigo LopezGazpio, and Lucia Specia. 2017. SemEval-2017 task 1: Semantic textual similarity multilingual and crosslingual focused evaluation. In Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017), Vancouver, Canada. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Stevie Chancellor, Eric PS Baumer, and Munmun De Choudhury. 20Who is the human in humancentered machine learning: The case of predicting mental health from social media. Proceedings of the ACM on Human-Computer Interaction, 3(CSCW):147.
    Google ScholarLocate open access versionFindings
  • Alexander D’Amour, Peng Ding, Avi Feller, Lihua Lei, and Jasjeet Sekhon. 2017. Overlap in observational studies with high-dimensional covariates. arXiv preprint arXiv:1711.02582.
    Findings
  • Munmun De Choudhury and Emre Kiciman. 2017. The language of social support in social media and its effect on suicidal ideation risk. In International AAAI Conference on Web and Social Media (ICWSM).
    Google ScholarLocate open access versionFindings
  • Munmun De Choudhury, Emre Kiciman, Mark Dredze, Glen Coppersmith, and Mrinal Kumar. 2016. Discovering shifts to suicidal ideation from mental health content in social media. In Proceedings of the 2016 CHI conference on human factors in computing systems, pages 2098–2110. ACM.
    Google ScholarLocate open access versionFindings
  • Matthew J Denny and Arthur Spirling. 2018. Text preprocessing for unsupervised learning: Why it matters, when it misleads, and what to do about it. Political Analysis, 26(2):168–189.
    Google ScholarLocate open access versionFindings
  • Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In North American Association of Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Vincent Dorie, Jennifer Hill, Uri Shalit, Marc Scott, and Daniel Cervone. 2019. Automated versus doit-yourself methods for causal inference: Lessons learned from a data analysis competition. Statistical Science, 34(1):43–68.
    Google ScholarLocate open access versionFindings
  • Long Duong, Trevor Cohn, Steven Bird, and Paul Cook. 2015. Low resource dependency parsing: Crosslingual parameter sharing in a neural network parser. In Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Felix Elwert and Christopher Winship. 2014. Endogenous selection bias: The problem of conditioning on a collider variable. Annual Review of Sociology, 40:31–53.
    Google ScholarLocate open access versionFindings
  • Seyed Amin Mirlohi Falavarjani, Hawre Hosseini, Zeinab Noorian, and Ebrahim Bagheri. 2017. Estimating the effect of exercising on users online behavior. In Eleventh International AAAI Conference on Web and Social Media.
    Google ScholarLocate open access versionFindings
  • Christian Fong and Justin Grimmer. 2016. Discovery of treatments from text corpora. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 1600–1609.
    Google ScholarLocate open access versionFindings
  • Wayne A Fuller. 1987. Measurement Error Models. John Wiley & Sons.
    Google ScholarFindings
  • Andrew Gelman and Eric Loken. 2013. The garden of forking paths: Why multiple comparisons can be a problem, even when there is no fishing expedition or p-hacking and the research hypothesis was posited ahead of time. Department of Statistics, Columbia University.
    Google ScholarLocate open access versionFindings
  • Amanda Gentzel, Dan Garant, and David Jensen. 2019. The case for evaluating causal models using interventional measures and empirical data. In Advances in Neural Information Processing Systems.
    Google ScholarLocate open access versionFindings
  • Adam Glynn and Konstantin Kashin. 2013. Front-door versus back-door adjustment with unmeasured confounding: Bias formulas for front-door and hybrid adjustments. In 71st Annual Conference of the Midwest Political Science Association, volume 3.
    Google ScholarLocate open access versionFindings
  • Brett R Gordon, Florian Zettelmeyer, Neha Bhargava, and Dan Chapsky. 2019. A comparison of approaches to advertising measurement: Evidence from big field experiments at facebook. Marketing Science, 38(2):193–225.
    Google ScholarLocate open access versionFindings
  • MA Hernn and JM Robins. 2020. Causal Inference: What If. Boca Raton: Chapman and Hall/CRC.
    Google ScholarFindings
  • Daniel E Ho, Kosuke Imai, Gary King, and Elizabeth A Stuart. 2007. Matching as nonparametric preprocessing for reducing model dependence in parametric causal inference. Political Analysis, 15(3):199– 236.
    Google ScholarLocate open access versionFindings
  • Paul W Holland. 1986. Statistics and causal inference. Journal of the American statistical Association, 81(396):945–960.
    Google ScholarLocate open access versionFindings
  • Stefano M Iacus, Gary King, and Giuseppe Porro. 2012. Causal inference without balance checking: Coarsened exact matching. Political Analysis.
    Google ScholarFindings
  • Guido W Imbens. 2000. The role of the propensity score in estimating dose-response functions. Biometrika, 87(3):706–710.
    Google ScholarLocate open access versionFindings
  • Guido W Imbens and Donald B Rubin. 2015. Causal Inference in Statistics, Social, and Biomedical Sciences. Cambridge University Press.
    Google ScholarLocate open access versionFindings
  • Mohit Iyyer, Varun Manjunatha, Jordan Boyd-Graber, and Hal Daume III. 2015. Deep unordered composition rivals syntactic methods for text classification. In Association for Computational Linguistics.
    Google ScholarFindings
  • David Jensen. 2019. Comment: Strengthening empirical evaluation of causal inference methods. Statistical Science, 34(1):77–81.
    Google ScholarLocate open access versionFindings
  • Fredrik Johansson, Uri Shalit, and David Sontag. 2016. Learning representations for counterfactual inference. In ICML.
    Google ScholarFindings
  • Katherine Keith and Brendan O’Connor. 2018. Uncertainty-aware generative models for inferring document class prevalence. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.
    Google ScholarLocate open access versionFindings
  • Emre Kiciman, Scott Counts, and Melissa Gasser. 2018. Using longitudinal social media analysis to understand the effects of early college alcohol use. In Twelfth International AAAI Conference on Web and Social Media.
    Google ScholarLocate open access versionFindings
  • Manabu Kuroki and Judea Pearl. 2014. Measurement bias and effect restoration in causal inference. Biometrika, 101(2):423–437.
    Google ScholarLocate open access versionFindings
  • Mark J Van der Laan and Sherri Rose. 2011. Targeted Learning: Causal Inference for Observational and Experimental Data. Springer Science & Business Media.
    Google ScholarFindings
  • Robert J LaLonde. 1986. Evaluating the econometric evaluations of training programs with experimental data. The American Economic Review, pages 604– 620.
    Google ScholarLocate open access versionFindings
  • Omer Levy, Yoav Goldberg, and Ido Dagan. 2015. Improving distributional similarity with lessons learned from word embeddings. Transactions of the Association for Computational Linguistics, 3:211–225.
    Google ScholarLocate open access versionFindings
  • Sheng Li, Nikos Vlassis, Jaya Kawale, and Yun Fu. 2016. Matching via dimensionality reduction for estimation of treatment effects in digital marketing campaigns. In IJCAI.
    Google ScholarLocate open access versionFindings
  • Christos Louizos, Uri Shalit, Joris M Mooij, David Sontag, Richard Zemel, and Max Welling. 2017. Causal effect inference with deep latent-variable models. In Advances in Neural Information Processing Systems.
    Google ScholarLocate open access versionFindings
  • Jared K Lunceford and Marie Davidian. 2004. Stratification and weighting via the propensity score in estimation of causal treatment effects: a comparative study. Statistics in Medicine, 23(19):2937–2960.
    Google ScholarLocate open access versionFindings
  • Subramani Mani and Gregory F Cooper. 2000. Causal discovery from medical textual data. In Proceedings of the AMIA Symposium, page 542. American Medical Informatics Association.
    Google ScholarLocate open access versionFindings
  • Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems.
    Google ScholarLocate open access versionFindings
  • Jacob M Montgomery, Brendan Nyhan, and Michelle Torres. 2018. How conditioning on posttreatment variables can ruin your experiment and what to do about it. American Journal of Political Science, 62(3):760–775.
    Google ScholarLocate open access versionFindings
  • Stephen L Morgan and Christopher Winship. 2015. Counterfactuals and Causal Inference. Cambridge University Press.
    Google ScholarFindings
  • Reagan Mozer, Luke Miratrix, Aaron Russell Kaufman, and L Jason Anastasopoulos. 2020. Matching with text data: An experimental evaluation of methods for matching documents and of measuring match quality. Political Analysis.
    Google ScholarFindings
  • Khanh Nguyen and Brendan OConnor. 2015. Posterior calibration and exploratory analysis for natural language processing models. In Empirical Methods in Natural Langugage Processing.
    Google ScholarLocate open access versionFindings
  • Huseyin Oktay, Akanksha Atrey, and David Jensen. 2019. Identifying when effect restoration will improve estimates of causal effect. In Proceedings of the 2019 SIAM International Conference on Data Mining, pages 190–198. SIAM.
    Google ScholarLocate open access versionFindings
  • Alexandra Olteanu, Onur Varol, and Emre Kiciman. 2017. Distilling the outcomes of personal experiences: A propensity-scored analysis of social media. In Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing, pages 370–386. ACM.
    Google ScholarLocate open access versionFindings
  • Judea Pearl. 2000. Causality: Models, Reasoning and Inference. Springer.
    Google ScholarFindings
  • Judea Pearl. 2009a. Causal inference in statistics: An overview. Statistics Surveys, 3:96–146.
    Google ScholarLocate open access versionFindings
  • Judea Pearl. 2009b. Causality: Models, Reasoning and Inference, Second edition. Cambridge University Press.
    Google ScholarFindings
  • Judea Pearl. 2014. Interpretation and identification of causal mediation. Psychological Methods, 19(4):459.
    Google ScholarLocate open access versionFindings
  • Judea Pearl, Madelyn Glymour, and Nicholas P Jewell. 2016. Causal Inference in Statistics: A Primer. John Wiley & Sons.
    Google ScholarFindings
  • James W Pennebaker, Martha E Francis, and Roger J Booth. 2001. Linguistic inquiry and word count: Liwc 2001. Mahway: Lawrence Erlbaum Associates, 71(2001):2001.
    Google ScholarFindings
  • Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In Empirical Methods in Natural Langugage Processing.
    Google ScholarLocate open access versionFindings
  • Thai T Pham and Yuanyuan Shen. 2017. A deep causal inference approach to measuring the effects of forming group loans in online non-profit microfinance platform. arXiv preprint arXiv:1706.02795.
    Findings
  • Jason Phang, Thibault Fevry, and Samuel R Bowman. 2018. Sentence encoders on stilts: Supplementary training on intermediate labeled-data tasks. arXiv preprint arXiv:1811.01088.
    Findings
  • Fermin Moscoso del Prado Martin and Christian Brendel. 2016. Case and cause in icelandic: Reconstructing causal networks of cascaded language changes. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2421–2430.
    Google ScholarLocate open access versionFindings
  • Jeremy A Rassen, Robert J Glynn, M Alan Brookhart, and Sebastian Schneeweiss. 2011. Covariate selection in high-dimensional propensity score analyses of treatment effects in small samples. American Journal of Epidemiology, 173(12):1404–1413.
    Google ScholarLocate open access versionFindings
  • Nils Reimers and Iryna Gurevych. 2019. SentenceBERT: Sentence embeddings using siamese BERTnetworks. In Empirical Methods in Natural Langugage Processing.
    Google ScholarLocate open access versionFindings
  • Thomas S Richardson and James M Robins. 2013. Single world intervention graphs (SWIGs): A unification of the counterfactual and graphical approaches to causality. Center for the Statistics and the Social Sciences, University of Washington Series. Working Paper, (128).
    Google ScholarLocate open access versionFindings
  • Margaret E Roberts, Brandon M Stewart, and Richard A Nielsen. 2020. Adjusting for confounding with text matching. American Journal of Political Science (forthcoming).
    Google ScholarLocate open access versionFindings
  • Margaret E Roberts, Brandon M Stewart, Dustin Tingley, Christopher Lucas, Jetson Leder-Luis, Shana Kushner Gadarian, Bethany Albertson, and David G Rand. 2014. Structural topic models for open-ended survey responses. American Journal of Political Science, 58(4):1064–1082.
    Google ScholarLocate open access versionFindings
  • Paul R Rosenbaum and Donald B Rubin. 1983. The central role of the propensity score in observational studies for causal effects. Biometrika, 70(1):41–55.
    Google ScholarLocate open access versionFindings
  • Paul R Rosenbaum and Donald B Rubin. 1984. Reducing bias in observational studies using subclassification on the propensity score. Journal of the American Statistical Association, 79(387):516–524.
    Google ScholarLocate open access versionFindings
  • Donald B Rubin. 1974. Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of Educational Psychology, 66(5):688.
    Google ScholarLocate open access versionFindings
  • Donald B Rubin. 2001. Using propensity scores to help design observational studies: application to the tobacco litigation. Health Services and Outcomes Research Methodology, 2(3-4):169–188.
    Google ScholarLocate open access versionFindings
  • Donald B Rubin. 2005. Causal inference using potential outcomes: Design, modeling, decisions. Journal of the American Statistical Association, 100(469):322–331.
    Google ScholarLocate open access versionFindings
  • Koustuv Saha, Benjamin Sugar, John Torous, Bruno Abrahao, Emre Kıcıman, and Munmun De Choudhury. 2019. A social media study on the effects of psychiatric medication use. In Proceedings of the International AAAI Conference on Web and Social Media, volume 13, pages 440–451.
    Google ScholarLocate open access versionFindings
  • Matthew Salganik. 2017. Bit By Bit: Social Research in the Digital Age. Princeton University Press.
    Google ScholarFindings
  • Tobias Schnabel, Igor Labutov, David Mimno, and Thorsten Joachims. 2015. Evaluation methods for unsupervised word embeddings. In Empirical Methods in Natural Langugage Processing.
    Google ScholarLocate open access versionFindings
  • Alexandra Schofield, Mans Magnusson, and David Mimno. 2017. Pulling out the stops: Rethinking stopword removal for topic models. In Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Narges Tabari, Piyusha Biswas, Bhanu Praneeth, Armin Seyeditabari, Mirsad Hadzikadic, and Wlodek Zadrozny. 2018. Causality analysis of twitter sentiments and stock market returns. In Proceedings of the First Workshop on Economics and Natural Language Processing. Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Chenhao Tan, Lillian Lee, and Bo Pang. 2014. The effect of wording on message propagation: Topicand author-controlled natural experiments on twitter. In Association for Computational Linguistics.
    Google ScholarLocate open access versionFindings
  • Tyler VanderWeele. 2015. Explanation in Causal Inference: Methods for Mediation and Interaction. Oxford University Press.
    Google ScholarFindings
  • Victor Veitch, Dhanya Sridhar, and David M Blei. 2019. Using text embeddings for causal inference. arXiv preprint arXiv:1905.12741.
    Findings
  • Hanna M Wallach, Iain Murray, Ruslan Salakhutdinov, and David Mimno. 2009. Evaluation methods for topic models. In Proceedings of the 26th Annual International Conference on Machine Learning, pages 1105–1112. ACM.
    Google ScholarLocate open access versionFindings
  • Zach Wood-Doughty, Ilya Shpitser, and Mark Dredze. 2018. Challenges of using text classifiers for causal inference. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4586–4598.
    Google ScholarLocate open access versionFindings
  • Zichao Yang, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola, and Eduard Hovy. 2016. Hierarchical attention networks for document classification. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
    Google ScholarLocate open access versionFindings
  • Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, and Kai-Wei Chang. 2017. Men also like shopping: Reducing gender bias amplification using corpus-level constraints. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.
    Google ScholarLocate open access versionFindings
  • William R Shadish, Margaret H Clark, and Peter M Steiner. 2008. Can nonrandomized experiments yield accurate answers? A randomized experiment comparing random and nonrandom assignments. Journal of the American Statistical Association, 103(484):1334–1344.
    Google ScholarLocate open access versionFindings
  • Dhanya Sridhar and Lise Getoor. 2019. Estimating causal effects of tone in online debates. In IJCAI.
    Google ScholarFindings
  • Dhanya Sridhar, Aaron Springer, Victoria Hollis, Steve Whittaker, and Lise Getoor. 2018. Estimating causal effects of exercise from mood logging data. In IJCAI/ICML Workshop on CausalML.
    Google ScholarLocate open access versionFindings
  • Elizabeth A Stuart. 2010. Matching methods for causal inference: A review and a look forward. Statistical Science, 25(1):1.
    Google ScholarLocate open access versionFindings
Your rating :
0

 

Tags
Comments