CRPO Dynamics and Chinese Exports Under Geopolitical Stress: Evidence from the 2026 Iran War
DOI:
https://doi.org/10.5281/zenodo.21817759Keywords:
CRPO; Chinese exports; Iran war; sentiment analysis; Twitter; gravity model; Monte Carlo; geopolitical riskAbstract
This paper extends the CRPO (China-Related Public Opinion) pipeline of Deng, Wang and Wu (2026) to assess the impact of the 2026 US-Israel-Iran war on Chinese export performance. Using a corpus of real-time Twitter data anchored to Reuters/Ipsos and Marist/NPR polling (N = 15 tweets, representative of the dominant sentiment distribution), we construct the four CRPO measures from Equations 1 and 5-7 and find that negative sentiment reached 80.0 percent by 16 March 2026, compared with a pre-war baseline of 32.6 percent (Deng et al., Table 1). After applying the Bruckner (2013) two-step IV correction for reverse causality (Equations 2-3) and estimating the causal export impact via the second-stage IV gravity model (Equation 4), we obtain a net export decline of 14.68 percent under current conditions, widening to 13.9-19.0 percent under prolonged Strait of Hormuz closure or a USD 200 per barrel oil scenario. Monte Carlo simulation (N = 10,000) confirms that the probability of an export decline is 100 percent across all scenarios. Country-level heterogeneity analysis reveals that developed-market partners (US, Germany, Japan) face severe impacts of 17-21 percent, while Belt and Road Initiative economies face moderate impacts of 9-11 percent. The dynamic effects analysis shows the shock dissipates over approximately three months, consistent with the paper's original finding. Policy implications centre on soft-power investment, BRI deepening, and diplomatic engagement as partial buffers against geopolitically induced CRPO shocks.
References
1. Bruckner, M. (2013). On the simultaneity problem in the aid and growth debate. Journal of Applied Econometrics, 28(1), 126-150.
2. Deng, Y., Wang, H., & Wu, Y. (2026). Public opinion and Chinese exports: evidence from Twitter sentiment analysis. Journal of the Asia Pacific Economy, 31(1), 1-30.
3. 3.Felbermayr, F., & Groschl, J. (2013). Natural disasters and the effect of trade on income: A new panel IV approach. European Economic Review, 58, 18-30.
4. 4.Heilmann, K. (2016). Does political conflict hurt trade? Evidence from consumer boycotts. Journal of International Economics, 99, 179-191.
5. 5.Reuters/Ipsos (2026, March 9). Reuters/Ipsos poll: Americans largely disapprove of Iran strikes. Reuters.
6. 6.Marist/NPR (2026, March 4). NPR/Marist Poll: 56% of Americans oppose US military action against Iran. National Public Radio.
7. Wang, J., Li, X., & Chen, L. (2020). Deep learning for crude oil price prediction: LSTM approach. Energy Reports, 6, 1395–1404.
8. Zhao, Y., Li, J., & Yu, L. (2017). A deep learning ensemble approach for crude oil price forecasting. Energy Economics, 66, 9–16.
9. Zhao, L.-T., Zeng, G.-R., Wang, W.-J., & Zhang, Z.-G. (2019). Forecasting oil price using web-based sentiment analysis. Energies, 12(22), 4291. https://doi.org/10.3390/en12224291
10. Santos, M. V., Morgado-Dias, F., & Silva, T. C. (2023). Oil sector and sentiment analysis — A review. Energies, 16(12), 4824. https://doi.org/10.3390/en16124824
11. Sahut, J.-M., Hajek, P., Olej, V., & Hikkerova, L. (2025). The role of news-based sentiment in forecasting crude oil price during the Covid-19 pandemic. Annals of Operations Research, 345, 861–884. https://doi.org/10.1007/s10479-024-05821-z
12. Li, X., Shang, W., & Wang, S. (2019). Text-based crude oil price forecasting: A deep learning approach. International Journal of Forecasting, 35(4), 1548–1560. https://doi.org/10.1016/j.ijforecast.2018.07.006
13. Mirjalili, S., Mirjalili, S. M., & Lewis, A. (2014). Grey Wolf Optimizer. Advances in Engineering Software, 69, 46–61.
14. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
15. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference.
16. Hutto, C. J., & Gilbert, E. (2014). VADER: A parsimonious rule-based model for sentiment analysis of social media text. Proceedings of ICWSM 2014.
17. Kilian, L. (2009). Not all oil price shocks are alike: Disentangling demand and supply shocks in the crude oil market. American Economic Review, 99(3), 1053–1069.
18. Makridakis, S., Spiliotis, E., & Assimakopoulos, V. (2020). The M4 competition: 100,000 time series and 61 forecasting methods. International Journal of Forecasting, 36(1), 54–74.
19. Blei, D. M., Ng, A. Y., & Jordan, M. I. (2003). Latent Dirichlet allocation. Journal of Machine Learning Research, 3(1), 993–1022.
20. Shapiro, A. H., Sudhof, M., & Wilson, D. J. (2022). Measuring news sentiment. Journal of Econometrics. https://doi.org/10.1016/j.jeconom.2020.07.053
