Extracting emerging events from social media: X/Twitter and the multilingual analysis of emerging geopolitical topics in near real time

John Burns; Tom Kelsey; Carl Donovan

doi:10.29329/jsomer.14

Authors

John Burns University of St Andrews https://orcid.org/0000-0002-2325-0235
Tom Kelsey University of St Andrews https://orcid.org/0000-0002-8091-1458
Carl Donovan University of St Andrews

DOI:

https://doi.org/10.29329/jsomer.14

Keywords:

Geopolitics, X / Twitter, Topic Modeling, Social Media Monitoring, Google Trends

Abstract

This study uses multiple languages to investigate the emergence of geopolitical topics on X / Twitter across two different time intervals: daily and hourly. For the daily interval, we examined the emergence of topics from February 4^th, 2023, to March 23^rd, 2023, at random three-hour intervals, compiling the topic modeling results for each day into a time series. For the hourly interval, we considered two days of data, June 1^st, 2023, and June 6^th, 2023, where we tracked the growth of topics for those days. We collected our data through the X / Twitter Filtered Stream using key bigrams (two-word phrases) for various geopolitical topics for multiple languages to identify emerging geopolitical events at the global and regional levels. Lastly, we compared the trends created by tracking emerging topics over time to Google Trends data, another data source for emerging topics. At the daily level, we found that our X / Twitter-based algorithm was able to identify multiple geopolitical events at least a day before they became relevant on Google Trends, and in the case of North Korean missile launches during this period, several languages identified more missile launches than the Google Trends data. As for the hourly data, we again found several topics that emerged hours before they started appearing on Google Trends. Our analyses also found that the different languages allowed for greater diversity in topics that would not have been possible if only one language had been used.

References

Research on 100 Million Tweets: What It Means for Your Social Media Strategy for Twitter. (2018). Vicinitas https://www.vicinitas.io/blog/twitter-social-media-strategy-2018-research-100-million-tweets#language.

Google Trends. (2025) Google https://trends.google.com/trends/?geo=US.

South Korea: 2021 Primary Energy Data in Quadrillion Btu. (2022). International, U.S Energy Information Administration. https://www.eia.gov/international/overview/country/KOR.

Total of 96.6% of Japan’s March Imports of Oil Came from Arab Countries, Led by Saudi Crude. (2023). Arab News, Arab News, https://www.arabnews.com/node/2294816/business-economy.

The Use of Arabic Diacritics. (2023). International House Cairo https://ihcairoeg.com/arabic/the-use-of-arabic-diacritics/.

Ahmed, A., & Xing, E.P. (2010). Timeline: A Dynamic Hierarchical Dirichlet Process Model for Recovering Birth/Death and Evolution of Topics in Text Stream. Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI2010). http://dx.doi.org/10.48550/arxiv.1203.3463.

Allahyari, M., & Kochut, K. (2015). Automatic Topic Labeling Using Ontology-Based Topic Models. 14th {IEEE} International Conference on Machine Learning and Applications, ICMLA 2015, December 9-11, 2015, pp. 259–64. doi:10.1109/ICMLA.2015.88.

Allan, J., Carbonell, J., Doddington, G., Yamron, J., & Yang, Y. (1998). Topic Detection and Tracking Pilot Study Final Report. Broadcast News Understanding and Transcription Workshop, pp. 194-218. http://ciir.cs.umass.edu/pubfiles/ir-137.pdf.

Amara, A., Taieb, M. A. H., & Aouicha, M. B. (2021). Multilingual Topic Modeling for Tracking Covid-19 Trends Based on Facebook Data Analysis. Applied Intelligence, 51(5), 3052-3073. http://dx.doi.org/10.1007/s10489-020-02033-3.

A. J. Blinken, Secretary of State. (2023). Sanctioning Operatives Involved in Iranian External Plots. U.S Department of State, June 1, 2023. https://www.state.gov/sanctioning-operatives-involved-in-iranian-external-plots/.

Atefeth, F., & Khreich, W. (2013). A Survery of Techniques for Event Detection in Twitter. Computational Intelligence, vol. 0, no. 0, 2013, https://citeseerx.ist.psu.edu/viewdoc/download

Baker, S. R., Bloom, N., & Davis, S. J. (2016). Measuring Economic Policy Uncertainty*. The Quarterly Journal of Economics, vol. 131, no. 4, 2016, pp. 1593-636, http://dx.doi.org/10.1093/qje/qjw024.

Baturo, A., Dasandi, N., & Mikhaylov, S. J. (2017). Understanding State Preferences with Text as Data: Introducing the Un General Debate Corpus. Research & Politics, vol. 4, no. 2, 2017, http://dx.doi.org/10.1177/2053168017712821.

Becker, H., Naaman, M., & Gravano, L. (2021). Beyond Trending Topics: Real-World Event Identification on Twitter. Proceedings of the International AAAI Conference on Web and Social Media, vol. 5, no. 1, 2021, pp. 438-41, doi:10.1609/icwsm.v5i1.14146.

Bekaert, G., Harvey, C. R., Lundblad, C. T., & Siegel, S. (2015). Political Risk and International Valuation (December 8, 2015). Columbia Business School Research Paper, No. 15-83, Available at SSRN: https://ssrn.com/abstract=2659257 or http://dx.doi.org/10.2139/ssrn.2659257

Besaw, C. (2021). Topic Modeling as Osint: Exploring Russian Presidential Speech Topics over Time. medium.com https://medium.com/the-die-is-forecast/topic-modeling-as-osint-exploring-russian-presidential-speech-topics-over-time-ad6018286d37.

Blei, D. M., & Lafferty J. D. (2006). Dynamic Topic Models. ACM Press, 2006. http://dx.doi.org/10.1145/1143844.1143859.

Blei, D. M, Ng A. Y., & Jordan, M. I. (2003). Latent Dirichlet Allocation. Journal of Machine Learning Research, vol. 3, 2003, pp. 993 - 1022, https://www.jmlr.org/papers/volume3/blei03a/blei03a.pdf.

Boyd-Graber, J., & Blei, D. M. (2009). Multilingual Topic Models for Unaligned Text. Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, AUAI Press, June 18 - 21 2009. doi:10.48550/arxiv.1205.2657.

Bremmer, I., & Kupchan., C. (2023). Top Risk 2023, Eurasia Group, January 3rd, 2023, pp. 1-30. general editor, Eurasia Group, https://www.eurasiagroup.net/issues/top-risks-2023.

Brewer, B. J. (2016). Stats 331: Introduction to Bayesian Statistics. Department of Statistics, University of Auckland, 2016.

Caldara, D., & Iacoviello, M. (2022). Measuring Geopolitical Risk. American Economic Review, vol. 112, no. 4, pp. 1194-225, http://dx.doi.org/10.1257/aer.20191823.

Chen, X., Liu, Z., Wei, L., Yan, J., Hao, T., & Ding, R. (2018). A Comparative Quantitative Study of Utilizing Artificial Intelligence on Electronic Health Records in the USA and China During 2008–2017. BMC Medical Informatics and Decision Making, vol. 18, no. S5, 2018, http://dx.doi.org/10.1186/s12911-018-0692-9.

Choi, H., & Varian, H. (2009). Predicting the Present with Google Trends. Google Inc., 2009, pp. 1-23. https://static.googleusercontent.com/media/www.google.com/en//googleblogs/pdfs/google_predictin g_the_present.pdf.

Choi, S. H., & Shin, H. (2023). North Korea Fires Two More Missiles into Its Pacific 'Firing Range'. Reuters, February 20th, 2023. https://www.reuters.com/world/asia-pacific/north-korea-fires-ballistic-missile-south-korea-military-2023-02-19/.

Contributors, Wikipedia. (2023) 1973 Oil Crisis. https://en.wikipedia.org/w/index.php?title=1973_oil_crisis&oldid=1161514686.

Contributors, Wikipedia. (2023) China–United States Relations. https://en.wikipedia.org/w/index.php?title=China%E2%80%93United_States_relations&oldid=1162607 472.

Contributors, Wikipedia. (2023) Cyberwarfare. https://en.wikipedia.org/w/index.php?title=Cyberwarfare&oldid=1160321593. A

Contributors, Wikipedia. (2023) Nuclear Warfare. https://en.wikipedia.org/w/index.php?title=Nuclear_warfare&oldid=1161701347.

Contributors, Wikipedia. (2023) Terrorism. https://en.wikipedia.org/w/index.php?title=Terrorism&oldid=1160928625.

Cordeiro, M. (2012). Twitter Event Detection: Combining Wavelet Analysis and Topic Inference Summarization. DSIE’12, the Doctoral Symposium on Informatics Engineering, https://www.researchgate.net/publication/281454053_Twitter_event_detection_combining_wavelet_analysis_and_topic_inference_summarization.

Culotta, A. (2010). Towards Detecting Influenza Epidemics by Analyzing Twitter Messages. Workshop on Social Media Analysis In conjunction with the International Conference on Knowledge Discovery & Data Mining (KDD 2010), July 25, 2010. http://snap.stanford.edu/soma2010/papers/soma2010_16.pdf.

Danilak, M. M. (2021). Langdetect. GitHub https://github.com/Mimino666/langdetect. 2021.

De Guzman, C. (2023). North Korea Is Ramping up Its Missile Tests. How Worried Should We Be? World - North Korea. Time https://time.com/6266737/north-korea-ballistic-missile-tests-2023/.

Duarte, R. (2025). Top 35 Social Media Platform (2025) Exploding Topics https://explodingtopics.com/blog/top-social-media-platforms

Faulconbridge, G. (2023)/ Nova Kakhovka Dam Breach: What Do We Know So Far? Reuters, June 7th 2023. https://www.reuters.com/world/europe/what-is-kakhovka-dam-ukraine-what-happened-2023- 06-07/.

Flint, C. (2022). Introduction to Geopolitics. Routledge, Taylor et Francis Group.

Fukuhara, T., Utsuro, T., & Nakagawa, H. (2005). Cross-Lingual Concern Analysis from Multilingual Weblog Articles. University of Tokyo https://citeseerx.ist.psu.edu/document?repid=rep1&type=pdf&doi=25b75750796c32780c044a791dfafc5105e73d5b.

Fukumasu, K., Eguchi K., & Xing, E. (2012). Symmetric Correspondence Topic Models for Multilingual Text Analysis. Advances in Neural Information Processing Systems 25 (NIPS 2012), edited by F. Pereira and C.J. Burges and L. Bottou and K.Q. Weinberger. http://www.cs.cmu.edu/~epxing/papers/2012/Fukumasu_Eguchi_Xing_NIPS12.pdf.

Goldstein, J. S. (1992). A Conflict-Cooperation Scale for Weis Events Data. The Journal of Conflict Resolution, vol. 36, no. 2, 1992, pp. 369-85, https://www.jstor.org/stable/174480.

Griffiths, T. L., & Steyvers, M. (2004). Finding Scientific Topics. Proceedings of the National Academy of Sciences, vol. 101, no. Supplement 1, 2004, pp. 5228-35, doi:10.1073/pnas.0307752101.

Grimmer, J., & Stewart, B. M. (2013). Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts. Political Analysis, vol. 21, no. 3, 2013, pp. 267-97, doi:10.1093/pan/mps028.

Groontendorst, M. (2022). BERTopic: Neural topic modeling with a class-based TF-IDF procedure, arXiv, https://arxiv.org/pdf/2203.05794

Hafezi, P. (2023). Iran Presents Its First Hypersonic Ballistic Missile, State Media Reports. Reuters, June 6, 2023. https://www.reuters.com/world/middle-east/iran-unveils-its-first-hypersonic-ballistic-missile-state-media-reports-2023-06-06/.

Hass, R. (2023). How Biden Could “Thaw” Us Relations with China. Brookings, May 23rd 2023. https://www.brookings.edu/articles/how-biden-could-thaw-us-relations-with-china/#:~:text=The%20year%202023%20was%20supposed,in%20the%20fall%20of%202023.

Hegazi, M. O., Al-Dossari, Y., Al-Yahy, A., Al-Sumari, A., & Hilal, A. (2021). Preprocessing Arabic Text on Social Media. Heliyon, vol. 7, no. 2, 2021, http://dx.doi.org/10.1016/j.heliyon.2021.e06191.

Hida, R., Takeishi, N., Yairi, T., & Hori, K. (2018). Dynamic and Static Topic Model for Analyzing Time-Series Document Collections. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, vol. Volume 2: Short Papers, Association for Computational Linguistics, pp. 516–20. doi:10.18653/v1/P18-2082.

Hisano, R., Sornette, D., Mizuno, T., Ohnishi, T., & Watanabe, T. (2013). High Quality Topic Extraction from Business News Explains Abnormal Financial Market Volatility. PLoS One, 8(6) e64846, http://dx.doi.org/10.1371/journal.pone.0064846.

Hong, L,, & Davison, B. D. (2010). Empirical Study of Topic Modeling in Twitter. Proceedings of the First Workshop on Social Media Analytics - SOMA '10, ACM Press, July 25, 2010. doi:10.1145/1964858.1964870.

Honnibal, M., & Montani. I. (2023). Spacy 2: Natural Language Understanding with Bloom Embeddings, Convolutional Neural Networks and Incremental Parsing. Explosion, https://spacy.io/usage.

Huang, T., Wu, F., Yu, J., & Zhang, B. (2014). International Political Risk and Government Bond Pricing. Journal of Banking and Finance, Forthcoming, 26th Australasian Finance and Banking Conference 2013, 2014, http://dx.doi.org/10.2139/ssrn.2312188.

Hurtado, J. L., Agarwal, A., & Zhu, X. (2016). Topic Discovery and Future Trend Forecasting for Texts. Journal of Big Data, vol. 3, no. 2, 2016, http://dx.doi.org/10.1186/s40537-016-0039-2.

Johnson, J. (2023). North Korea Fires Short-Range Missile Ahead of U.S.-South Korea Military Exercises. The Japan Times, March 9th 2023. https://www.japantimes.co.jp/news/2023/03/09/asia-pacific/north-korea-missile-launch-march-9/.

Kapadia, S. (2019). Evaluate Topic Models: Latent Dirichlet Allocation (Lda), Towards Data Science https://towardsdatascience.com/evaluate-topic-model-in-python-latent-dirichlet-allocation-lda-7d57484bb5d0.

Karim, A. A., & Abandah, G., (2021). On the Training of Deep Neural Networks for Automatic Arabic-Text Diacritization. (IJACSA) International Journal of Advanced Computer Science and Applications, vol. 12, no. 8, 2021, pp. 276-86, https://thesai.org/Downloads/Volume12No8/Paper_32- On_the_Training_of_Deep_Neural_Networks.pdf.

Klement, J. (2021). Geo-Economics: The Interplay between Geopolitics, Economics, and Investments. CFA Institute. Research Foundation Books.

Koren, V. (2022). Korean Tokenization & Lemmatization. Medium https://korenv20.medium.com/korean-tokenization-lemmatization-a741fc9939cc.

Kravariti, A. (2023) Machine Vs Human Translation: The Pros, Cons and When to Use Each. Blog. translate plus https://www.translateplus.com/blog/machine-vs-human-translation-pros-cons-use/.

Kulshrestha, R. (2022) A Beginner’s Guide to Latent Dirichlet Allocation (Lda). Towards Data Science https://towardsdatascience.com/latent-dirichlet-allocation-lda-9d1cd064ffa2.

Lakezina, V. (2023) War Zone Villagers Flee after Massive Ukraine Dam Destroyed. Reuters, June 6th, 2023. https://www.reuters.com/world/europe/russia-says-it-thwarts-another-major-ukrainian-offensive-donetsk-2023-06-05/.

Lee, H., & Song, J. (2020). Understanding Recurrent Neural Network for Texts Using English-Korean Corpora. Communications for Statistical Applications and Methods, vol. 27, no. 3, 2020, pp. 313-26, https://doi.org/10.29220/CSAM.2020.27.3.313.

Lee, J. J., Kwon, S. B., & Ahn, S. M. (2018). Sentiment Analysis Using Deep Learning Model Based on Phoneme-Level Korean. Journal of Information Technology Services, vol. 17, no. 1, 2018, pp. 79-89, https://doi.org/10.9716/KITS.2018.17.1.079.

Lee, K., Agrawal, A., & Choudhary, A. (2017). Forecasting Influenza Levels Using Real-Time Social Media Streams. IEEE, 2017. doi:10.1109/ichi.2017.68.

Lind, F., Eberl, J. M., Galyga, S., Heidenreich, T., Boomgaarden, H. G., Jiménez, B. H., & Berganza, R. (2019). A Bridge over the Language Gap: Topic Modelling for Text Analyses across Languages for Country Comparative Research. Working Paper, Reminder, November 2019. https://www.reminder-project.eu/wp-content/uploads/2019/11/D8.7.pdf.

Martin, M. (2023). 29 Twitter Stats That Matter to Marketers in 2023. Strategy. Hootsuite, https://blog.hootsuite.com/twitter-statistics/.

Massicotte, P., & Eddelbuettel, D. (2022). Gtrendsr: Perform and Display Google Trends Queries. 1.5.1 ed., CRAN, https://github.com/PMassicotte/gtrendsR.

Metzler, D., Cai, C., & Hovy, E. (2012). Structured Event Retrieval over Microblog Archives. Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, pp. 646–55.

Nidhaloff, (2020). Deep-Translator. GitHub, https://github.com/nidhaloff/deep-translator.

Peersman, G., & Smets, F. (2002). "The Industry Effects of Monetary Policy in Euro Area." Working Paper Series, edited by European Central Bank, https://www.ecb.europa.eu/pub/pdf/scpwps/ecbwp165.pdf.

Pelgrim, R. (2023). "Arabic Nlp: Unique Challenges and Their Solutions." Medium https://towardsdatascience.com/arabic-nlp-unique-challenges-and-their-solutions-d99e8a87893d.

Psaledakis, D, (2023). "Us Slaps Sanctions on Iranian, Chinese Targets over Tehran's Missile, Military Programs." Reuters, June 6, 2023. https://www.reuters.com/world/middle-east/us-slaps-sanctions-iranian-chinese-targets-action-over-tehrans-missile-military-2023-06-06/.

Ranaei, S., Arho, S., Porter, A., & Carley, S. (2020). Evaluating Technological Emergence Using Text Analytics: Two Case Technologies and Three Approaches. Scientometrics, vol. 122, no. 1, 2020, pp. 215-47, http://dx.doi.org/10.1007/s11192-019-03275-w.

Rehurek, R., & Sojka, P. (2010). Software Framework for Topic Modelling with Large Corpora. Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks, ELRA, https://pypi.org/project/gensim/.

Reimers, N., & Gurevych, I. (2019). Sentence - BERT: Sentence Embeddings using Siamese BERT - Networks, CoRR, https://arxiv.org/pdf/1908.10084

Reuter, K., Zhu, Y., Angyan, P., Le, N. Q., Merchant, A. A., & Zimmer, M. (2019). Public Concern About Monitoring Twitter Users and Their Conversations to Recruit for Clinical Trials: Survey Study. Computer Science Faculty Research and Publications. 29. https://epublications.marquette.edu/comp_fac/29

Reuters. (2023). France Plans Major Police Presence for June 6 Day of Protest. Reuters, Reuters, June 4th, 2023. https://www.reuters.com/world/europe/france-plans-major-police-presence-june-6-day-protest- 2023-06-04/.

Revert, F. (2021). An Overview of Topics Extraction in Python with Lda. Towards Data Science https://towardsdatascience.com/the-complete-guide-for-topics-extraction-in-python-a6aaa6cedbbc.

Rill, S., Reinel, D., Scheidt, J., & Zicari, R. V. (2014). Politwi: Early Detection of Emerging Political Topics on Twitter and the Impact on Concept-Level Sentiment Analysis. Knowledge-Based Systems, vol. 69, pp. 24-33, https://doi.org/10.1016/j.knosys.2014.05.008.

Roberts, M. E., Stewart, B. M., Tingley, D., & Airoldi, E. M. (2013). The Structural Topic Model and Applied Social Science. Neural Information Processing Society, https://scholar.princeton.edu/files/bstewart/files/stmnips2013.pdf.

Ryall, J. (2023). Older Drivers in Japan Are Mixing up Their Accelerate and Brake Pedals with Fatal Results. East Asia. South China Morning Press https://www.scmp.com/news/asia/east-asia/article/2050472/older-drivers-japan-are-mistaking-stop-and-go-fatal-results.

Sakamoto, T. & Takikawa, H. (2017). Cross-National Measurement of Polarization in Political Discourse: Analyzing Floor Debate in the U.S. The Japanese Legislatures. IEEE International Conference on Big Data (Big Data), IEEE, doi:10.1109/bigdata.2017.8258285.

Seo, Y., Lendon, B., & Ogura, J. (2023). North Korea Says It Tested Icbm in Surprise Drill. CNN, February 18th, 2023. https://www.cnn.com/2023/02/18/asia/north-korea-missile-launch-intl-hnk-ml/index.html.

Shahrokhi, S. (2023). Iran News in Brief – June 1, 2023. National Council of Resistance of Iran https://www.ncr-iran.org/en/news/iran-news-in-brief-june-1-2023/.

Taira, B. R., Kreger, V., Orue, A., & Diamond, L. C. (2021). A Pragmatic Assessment of Google Translate for Emergency Department Instructions. Journal of General Internal Medicine, vol. 36, no. 11, pp. 3361-5, doi: 10.1007/s11606-021-06666-z.

Tetlock, P. C., Saar-Tsechansky, M., & MacSkassy, S. (2008). More Than Words: Quantifying Language to Measure Firms' Fundamentals. The Journal of Finance, vol. 63, no. 3, pp. 1437-67, doi:10.1111/j.1540-6261.2008.01362.x.

Twitter. (2022). Filtered Stream. Twitter. https://developer.twitter.com/en/docs/twitter-api/tweets/filteredstream/integrate/build-a-rule.

Urquhart, A. (2018). What Causes the Attention of Bitcoin? Economics Letters, vol. 166, pp. 40-44, doi:10.1016/j.econlet.2018.02.017.

Wallach, H. M., Murray, I., Salakhutdinov, R., & Mimno, D. (2009). Evaluation Methods for Topic Models. Proceedings of the 26th Annual International Conference on Machine Learning - ICML '09, ACM Press, doi:10.1145/1553374.1553515.

Wang, X., & McCallum, A. (2006). Topics over Time: A Non-Markov Continuous-Time Model of Topical Trends. Conference on Knowledge Discovery and Data Mining (KDD), edited by ACM, ACM. https://people.cs.umass.edu/~mccallum/papers/tot-kdd06s.pdf.

Wieringa, J. (2023). Ways to Compute Topics over Time, Part 1. https://jeriwieringa.com/2017/06/21/Calculating-and-Visualizing-Topic-Significance-over-Time-Part- 1/.

Yang, W, Boyd-Graber, J., & Resnik, P. (2019). A Multilingual Topic Model for Learning Weighted Topic Links across Corpora with Low Comparability. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Association for Computational Linguistics, pp. 1243–48. doi:10.18653/v1/d19.

Yim, H. (2023). North Korea Fires Ballistic Missile as U.S.-South Korean Drills Go On. Reuters, March 19th, 2023. https://www.reuters.com/world/asia-pacific/north-korea-fired-ballistic-missile-towards-sea-off-east-coast-yonhap-2023-03-19/.

Yuan, M., Van Durme, B., & Boyd-Graber, J. (2018). Multilingual Anchoring: Interactive Topic Modeling and Alignment Across Languages. 32nd Conference on Neural Information Processing System (NeurIPS 2018), https://forest-snow.github.io/docs/2018_nips_mtanchor.pdf

Yuning, C., & Lianzhong, L. (2016). "Development and Research of Topic Detection and Tracking." IEEE, doi:10.1109/icsess.2016.7883041.

Zheng, L., Nie, T., Moriya, I., Inoue, Y., Imada, T., Utsuro, T., Kawada, Y., & Kando, N. (2014). Comparative Topic Analysis of Japanese and Chinese Bloggers. 28th International Conference on Advanced Information Networking and Applications Workshops, IEEE, doi:10.1109/waina.2014.107.

Zosa, E., & Pivovarova, L. (2022). Multilingual and Multimodal Topic Modelling with Pretrained Embedding. Proceedings of the 29th International Conference on Computational Linguistics, ACL, October 12th-17th. https://aclanthology.org/2022.coling-1.355.pdf

@Gesu_audio. (2018). Japanese Prius Missile. Twitter, November 18th, 2018. https://twitter.com/Gesu_audio/status/1064073144355287041.