From empathy to exclusion: how Immigrant groups are framed in online discourse
DOI:
https://doi.org/10.47989/ir31iConf64261Keywords:
Moral foundations, Immigration,, Social media discourse, Large language modelingAbstract
Introduction. When examining moral foundations in immigration discourse on social media, most studies focus on ideology-based groups rather than across specific immigrant groups. This ignores moral framings that depict some communities with empathy and others as threats. This research explores how moral foundations vary in Twitter conversations about five immigrant groups.
Method. Tweets were sorted into five categories (based on immigrant groups being discussed: African, Asian, European, Latin American, or Middle Eastern) utilising keyword searches and AI LLM modeling. GPT-3.5 Turbo was employed and achieved a satisfactory performance (0.83) compared to manual human labeling.
Analysis. Scores for foundation variables (care/harm, fairness/cheating, loyalty/betrayal, authority/subversion, and purity/sanctity) were analysed using enhMFD1 dictionary. One-way ANOVA tested overall differences between groups and Tukey’s HSD post-hoc test identified specific patterns.
Results. Latin American immigrant discourse emphasised care and authority. European-focused tweets featured stronger loyalty. African immigrant discourse highlighted loyalty with moderate authority, discourse about Middle Eastern immigrants showed elevated harm and betrayal, and Asian immigrant discourse portrayed higher fairness-vice.
Conclusion(s). Immigrant groups are framed differently through moral language in social media conversations, which may influence perceptions and can inform strategies for addressing harmful narratives on social media.
References
Arunasalam, A., Farrukh, H., Tekcan, E., & Celik, Z. B. (2024). An exploration of online toxic content against refugees. In Symposium on Usable Security and Privacy (USEC).
Bail, C. A. (2012). The fringe effect: Civil society organisations and the evolution of media discourse about Islam since the September 11th attacks. American Sociological Review, 77(6), 855-879.
Bonilla-Silva, E. (2004). From bi-racial to tri-racial: Towards a new system of racial stratification in the USA. Ethnic and racial studies, 27(6), 931-950.
Boyd, D. (2010). Social network sites as networked publics: Affordances, dynamics, and implications. In A networked self (pp. 47-66). Routledge.
Brubaker, R. (2004). Ethnicity without groups. Harvard university press.
Chouliaraki, L., & Zaborowski, R. (2017). Voice and community in the 2015 refugee crisis: A content analysis of news coverage in eight European countries. International Communication Gazette, 79(6-7), 613-635.
Conzo, P., Fuochi, G., Anfossi, L., Spaccatini, F., & Mosso, C. O. (2021). Negative media portrayals of immigrants increase ingroup favoritism and hostile physiological and emotional reactions. Scientific Reports, 11(1), 16407.
Davidson, T., Warmsley, D., Macy, M., & Weber, I. (2017, May). Automated hate speech detection and the problem of offensive language. In Proceedings of the international AAAI conference on web and social media (Vol. 11, No. 1, pp. 512-515).
Gilardi, F., Alizadeh, M., & Kubli, M. (2023). ChatGPT outperforms crowd workers for text-annotation tasks. Proceedings of the National Academy of Sciences, 120(30), e2305016120.
Graham, J., Haidt, J., Koleva, S., Motyl, M., Iyer, R., Wojcik, S. P., & Ditto, P. H. (2013). Moral foundations theory: The pragmatic validity of moral pluralism. In Advances in Experimental Social Psychology (Vol. 47, pp. 55–130). Academic Press.
Grootendorst, M. (2022). BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794.
Grover, T., Bayraktaroglu, E., Mark, G., & Rho, E. H. R. (2019). Moral and affective differences in US immigration policy debate on Twitter. Computer Supported Cooperative Work (CSCW), 28(3), 317–355. https://doi.org/10.1007/s10606-019-09365-0
Hoewe, J., Panek, E., Peacock, C., Sherrill, L., & Wheeler, S. (2021). Using moral foundations to assess stereotypes: Americans’ perceptions of immigrants and refugees. Journal of Immigrant & Refugee Studies, 20(4), 501–518. https://doi.org/10.1080/15562948.2021.1949657
Hofstra, B., & de Schipper, N. C. (2018). Predicting ethnicity with first names in online social media networks. Big Data & Society, 5(1), 2053951718761141. https://doi.org/10.1177/2053951718761141
Khatua, A., & Nejdl, W. (2023, September). Why do we hate migrants? A double machine learning-based approach. In Proceedings of the 34th ACM Conference on Hypertext and Social Media (pp. 1–10).
Koltsova, O., Nikolenko, S., Alexeeva, S., Nagornyy, O., & Koltcov, S. (2017, June). Detecting interethnic relations with the data from social media. In International Conference on Digital Transformation and Global Society (pp. 16–30). Cham: Springer International Publishing.
Luttrell, A., & Trentadue, J. T. (2024). Advocating for mask-wearing across the aisle: Applying moral reframing in health communication. Health Communication, 39(2), 270-282.
Menshikova, A., & van Tubergen, F. (2022). What drives anti-immigrant sentiments online? A novel approach using Twitter. European Sociological Review, 38(5), 694–706. https://doi.org/10.1093/esr/jcac021
O’Connor, A., & Shumate, M. (2020). A multidimensional network approach to strategic communication. In Future directions of strategic communication (pp. 71-88). Routledge.
Pierre, J. (2004). Black immigrants in the United States and the’ cultural narratives’ of ethnicity. Identities: Global studies in culture and power, 11(2), 141-170.
Papacharissi, Z. (2015). Affective publics: Sentiment, technology, and politics. Oxford University Press.
Rezapour, R., Shah, S. H., & Diesner, J. (2019, June). Enhancing the measurement of social effects by capturing morality. In Proceedings of the Tenth Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (pp. 35–45).
Rubenzer, T. (2016). Social media foreign policy: Examining the political use of social media by ethnic identity groups in the United States. Politics, 36(2), 153–168.
Santa Ana, O. (2002). Brown tide rising: Metaphors of Latinos in contemporary American public discourse. University of Texas Press.https://doi.org/10.1111/1467-9256.12109
Törnberg, P. (2023). Chatgpt-4 outperforms experts and crowd workers in annotating political twitter messages with zero-shot learning. arXiv preprint arXiv:2304.06588.
Whitfield, C., Liu, Y., & Anwar, M. (2025). Impact of COVID-19 pandemic on social determinants of health issues of marginalised Black and Asian communities: A social media analysis empowered by natural language processing. Journal of Racial and Ethnic Health Disparities, 12(3), 1641–1656. https://doi.org/10.1007/s40615-024-01927-7
Wu, E. D. (2014). The colour of success: Asian Americans and the origins of the model minority. Princeton University Press.
Yang, A., Choi, I. M., Abeliuk, A., & Saffer, A. (2021). The influence of interdependence in networked publics spheres: How community-level interactions affect the evolution of topics in online discourse. Journal of Computer-Mediated Communication, 26(3), 148-166.
Yang, A., & Saffer, A. J. (2020). Standing out in a networked communication context: Toward a network contingency model of public attention. New Media & Society, 23(10), 2902–2925. https://doi.org/10.1177/1461444820939445
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Kirin Mohile , Yiqi Li
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
