Abstract
There has been an upward trend of fake news propagation on social media. To solve the fake news propagation problem, it is crucial to understand which media posts (e.g., tweets) cause fake news to disseminate widely, and further what lexicons inside a tweet play essential roles for the propagation. However, only modeling the correlation between social media posts and dissemination will find a spurious relationship between them, provide imprecise dissemination prediction, and incorrect important lexicons identification because it did not eliminate the effect of the confounder variable. Additionally, existing causal inference models cannot handle numerical and textual covariates simultaneously. Thus, we propose a novel causal inference model that combines the textual and numerical covariates through soft-prompt learning, and removes irrelevant information from the covariates by conditional treatment generation toward learning effective confounder representation. Then, the model identifies critical lexicons through a post-hoc explanation method. Our model achieves the best performance against baseline methods on two fake news benchmark datasets in terms of dissemination prediction and important lexicon identification related to the dissemination. The code is available at https://github.com/bigheiniu/CausalFakeNews.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A news tweet means a tweet mentions a certain news.
- 2.
We leave the syntax self-interpreted causal inference model as our future work.
- 3.
Due to space limit, we only report the fake news’ tweets.
References
Aldous, K.K., An, J., Jansen, B.J.: View, like, comment, post: analyzing user engagement by topic at 4 levels across 5 social media platforms for 53 news organizations. In: ICWSM (2019)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
Chen, H., Ji, Y.: Learning variational word masks to improve the interpretability of neural text classifiers. In: EMNLP (2020)
Cheng, L., Guo, R., Shu, K., Liu, H.: Causal understanding of fake news dissemination on social media. In: KDD (2021)
Deng, Z., Zheng, X., Tian, H., Zeng, D.D.: Deep causal learning: representation, discovery and inference. arXiv preprint arXiv:2211.03374 (2022)
Egami, N., Fong, C.J., Grimmer, J., Roberts, M.E., Stewart, B.M.: How to make causal inferences using texts. CoRR abs/1802.02163 (2018)
Fytas, P., Rizos, G., Specia, L.: What makes a scientific paper be accepted for publication? (2021)
Indhiarti, T.R., Chaerunnisa, E.R.: A corpus-driven collocation analysis of degree adverb very, really, quite, and pretty (2020)
Keith, K.A., Jensen, D., O’Connor, B.: Text and causal inference: a review of using text to remove confounding from causal estimates. In: ACL (2020)
Kilgo, D.K., Sinta, V.: Six things you didn’t know about headline writing: sensationalistic form in viral news content from traditional and digitally native news organizations. In: ISOJ, vol. 6, pp. 111–130 (2016)
Kushin, M.J., Yamamoto, M.: Did social media really matter? college students’ use of online media and political decision making in the 2008 election. Mass Commun. Soc. 13(5), 608–630 (2010)
Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: EMNLP (2021)
Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: ACL (2020)
Liu, X., Zheng, Y., Du, Z., Ding, M., Qian, Y., Yang, Z., Tang, J.: Gpt understands, too (2021)
Louizos, C., Shalit, U., Mooij, J.M., Sontag, D., Zemel, R., Welling, M.: Causal effect inference with deep latent-variable models. In: NeurIPS (2017)
Miao, W., Geng, Z., Tchetgen Tchetgen, E.J.: Identifying causal effects with proxy variables of an unmeasured confounder. Biometrika 105(4), 987–993 (2018)
Nguyen, D.: Comparing automatic and human evaluation of local explanations for text classification. In: NAACL HLT (2018)
Park, K., Kwak, H., An, J., Chawla, S.: How-to present news on social media: a causal analysis of editing news headlines for boosting user engagement. In: ICWSM (2021)
Pearl, J.: Causality. Cambridge University Press, Cambridge (2009)
Pearl, J., Bareinboim, E.: Transportability of causal and statistical relations: a formal approach. In: AAAI (2011)
Petrovic, S., Osborne, M., Lavrenko, V.: RT to win! predicting message propagation in twitter. In: ICWSM, The AAAI Press (2011)
Pryzant, R., Basu, S., Sone, K.: Interpretable neural architectures for attributing an ad’s performance to its writing style. In: EMNLP Workshop BlackboxNLP (2018)
Pryzant, R., Card, D., Jurafsky, D., Veitch, V., Sridhar, D.: Causal effects of linguistic properties. In: NAACL HLT (2021)
Pryzant, R., joo Chung, Y., Jurafsky, D.: Predicting sales from the language of product descriptions. In: eCOM@SIGIR (2017)
Pryzant, R., Shen, K., Jurafsky, D., Wagner, S.: Deconfounded lexicon induction for interpretable social science (2018)
Qin, G., Eisner, J.: Learning how to ask: Querying LMS with mixtures of soft prompts. In: NAACL-HLT (2021)
Ribeiro, M.T., Singh, S., Guestrin, C.: "why should I trust you?": Explaining the predictions of any classifier. In: KDD (2016)
Samek, W., Binder, A., Montavon, G., Lapuschkin, S., Müller, K.: Evaluating the visualization of what a deep neural network has learned. IEEE Trans. Neural Netw. Learn. Syst 28(11), 2660–2673 (2017)
Shi, C., Blei, D.M., Veitch, V.: Adapting neural networks for the estimation of treatment effects. In: NeurIPS (2019)
Shu, K., Mahudeswaran, D., Wang, S., Lee, D., Liu, H.: Fakenewsnet: a data repository with news content, social context and dynamic information for studying fake news on social media. arXiv preprint arXiv:1809.01286 (2018)
Shu, K., Sliva, A., Wang, S., Tang, J., Liu, H.: Fake news detection on social media: a data mining perspective. ACM SIGKDD Explor. Newsl. 19(1), 22–36 (2017)
Strekalova, Y.A., Krieger, J.L.: Beyond words: amplification of cancer risk communication on social media. J. Health Commun. 22(10), 849–857 (2017)
Suh, B., Hong, L., Pirolli, P., Chi, E.H.: Want to be retweeted? large scale analytics on factors impacting retweet in twitter network. In: SocialCom (2010)
Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)
Vosoughi, S., Roy, D., Aral, S.: The spread of true and false news online. Science 359(6380), 1146–1151 (2018)
Zhang, Y.F., Zhang, H., Lipton, Z.C., Li, L.E., Xing, E.P.: Can transformers be strong treatment effect estimators? arXiv preprint arXiv:2202.01336 (2022)
Acknowledgement
This work was supported in part by NSF grant CNS-1755536 and WPI TRIAD. Any opinions, findings and conclusions or recommendations expressed in this material are the author(s) and do not necessarily reflect those of the sponsors.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Li, Y., Lee, K., Kordzadeh, N., Guo, R. (2023). What Boosts Fake News Dissemination on Social Media? A Causal Inference View. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13938. Springer, Cham. https://doi.org/10.1007/978-3-031-33383-5_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-33383-5_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33382-8
Online ISBN: 978-3-031-33383-5
eBook Packages: Computer ScienceComputer Science (R0)