Elamur Research⌕
☰
home / papers / 2026 / Modeling Cultural and Subcultural Variation in Code-Switched Discourse with Topic Annotation

Modeling Cultural and Subcultural Variation in Code-Switched Discourse with Topic Annotation

Paper · 2026 · Nemika Tyagi, Nelvin Licona-Guevara and Olga Kellert

Summary

NLP research on code-switching has mostly focused on token-level questions, such as where a switch happens or which language is the matrix language. It has paid little attention to why speakers switch, or to how social and cultural context shapes switching. The authors suggest topic-based annotation as a comparative lens for this question.

They used gpt-4.1-2025-04-14 to label 3,691 intra-sententially code-switched sentences from two sources: Spanish-English conversations in the Miami corpus and Spanish-Guaraní tweets and news from the GUA-SPA shared task. Labels cover topics and discourse dimensions. The annotation schemas were built inductively for each corpus, and the labels were linked to speaker metadata such as gender and language dominance.

The analysis finds that topics, language choice and social variables are systematically related. Subgroups within the Miami community behave differently, while the Paraguayan data shows a diglossic split between formal and informal domains. The work matters because it gives cross-cultural NLP a scalable, interpretable and cheaper way to enrich bilingual corpora, including low-resource ones, with discourse-level labels.

Key points

  • Data: 2,825 code-switched sentences from the Miami corpus (84 speakers, 29.7k tokens, about 10.5 tokens per sentence) and 866 from the GUA-SPA training portion (15.6k tokens, about 18.0 tokens per sentence).
  • Schemas: Two bilingual annotators drafted the schemas by reviewing 30 random sentences per corpus.
    • Miami is tagged for Topics and Functions, e.g., DiscourseMarker, Quotation, Humor, SolidarityIdentity.
    • Spanish-Guaraní is tagged for Formality, Genre and Topic.
  • Annotation setup: gpt-4.1-2025-04-14 ran deterministically (temp=0, max tokens=200) in batches of 50–100 sentences, with outputs normalized to canonical labels and checked manually.
  • Findings:
    • Miami shows gender- and dominance-related asymmetries.
    • Paraguay shows diglossia, with Guaraní linked to formal domains and Spanish to informal ones.
  • Resource: The annotated datasets are released at github.com/N3mika/topicmodelling.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Arizona State UniversityTempe · United States50 works · 2,032 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Discourse analysis · 466 works

Cite

Cite as Nemika Tyagi, Nelvin Licona-Guevara and Olga Kellert. 2026. Modeling Cultural and Subcultural Variation in Code-Switched Discourse with Topic Annotation. Proceedings of the 4th Workshop on Cross-Cultural Considerations in NLP (C3NLP 2026).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.c3nlp-1.3

@inproceedings{tyagi2026modeling,
  title = {{Modeling Cultural and Subcultural Variation in Code-Switched Discourse with Topic Annotation}},
  author = {Nemika Tyagi, Nelvin Licona-Guevara and Olga Kellert},
  booktitle = {Proceedings of the 4th Workshop on Cross-Cultural Considerations in NLP (C3NLP 2026)},
  year = {2026},
  doi = {10.18653/v1/2026.c3nlp-1.3},
  url = {https://doi.org/10.18653/v1/2026.c3nlp-1.3}
}

References

20 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Federico Bianchi, Silvia Terragni, and Dirk Hovy. 2021. Pre-training is a hot topic: Contextualized document embeddings improve topic coherence. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language…
  2. Olga Kellert and Nicholas Hill Matlis. 2022. Social context and user profiles of linguistic variation on a micro scale. In Proceedings of the Ninth Workshop on NLP for Similar Languages, Varieties and Dialects, pages 14–19, Gyeongju, Republic of Korea. Association for Computational Linguistics. find
  3. Olga Kellert, Nemika Tyagi, Muhammad Imran, Nelvin Licona-Guevara, and Carlos Gómez-Rodrı́guez. 2025. Parsing the switch: Llm-based ud annotation for complex code-switched and low-resource languages. arXiv preprint arXiv:2506.07274.
  4. Su Lin Blodgett, Lisa Green, and Brendan O’Connor. 2016. Demographic dialectal variation in social media: A case study of African-American English. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1119–1130, Austin, Texas. Association for Computational…
  5. Chen Cecilia Liu, Iryna Gurevych, and Anna Korhonen. 2025. Culturally aware and adapted NLP: A taxonomy and a survey of the state of the art. Transactions of the Association for Computational Linguistics, 13:652–689.
  6. Barbara E. Bullock and Almeida Jacqueline Toribio. 2009. Themes in the study of code-switching, page 1–18. Cambridge Handbooks in Language and Linguistics. Cambridge University Press. find
  7. Carol Myers-Scotton. 1993. Social Motivations For Codeswitching: Evidence from Africa. Oxford University Press. find
  8. Roman Egger and Joanne Yu. 2022. A topic modeling comparison between lda, nmf, top2vec, and bertopic Dong Nguyen, A. Seza Doğruöz, Carolyn P. Rosé, and Franciska de Jong. 2016. Computational sociolinguistics: A Survey. Computational Linguistics, 42(3):537–593.
  9. Ruochen Zhang, Samuel Cahyawijaya, Jan Christian Blaise Cruz, Genta Winata, and Alham Fikri Aji. 2023. Multilingual large language models are not (yet) code-switchers. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 12567–12582, Singapore. Association…
  10. Parth Patwa, Gustavo Aguilar, Sudipta Kar, Suraj Pandey, Srinivas PYKL, Björn Gambäck, Tanmoy Chakraborty, Thamar Solorio, and Amitava Das. 2020. SemEval-2020 task 9: Overview of sentiment analysis of code-mixed tweets. In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 774–79…
  11. Naitian Zhou, David Bamman, and Isaac L Bleaman. 2025. Culture is not trivia: Sociocultural theory for cultural nlp. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 25869–25886.
  12. Edoardo Maria Ponti, Goran Glavaš, Olga Majewska, Qianchu Liu, Ivan Vulić, and Anna Korhonen. 2020. XCOPA: A multilingual dataset for causal commonsense reasoning. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2362–2376, Online. Associatio…
  13. Shana Poplack. 1980. Sometimes i’ll start a sentence in spanish y termino en espaÑol: toward a typology of code-switching1. Linguistics, 18(7-8):581–618. find
  14. Tom Potter and Zheng Yuan. 2024. Llm-based code-switched text generation for grammatical error correction. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 16957–16965. find
  15. Joan Rubin. 1962. Bilingualism in paraguay. Anthropological Linguistics, 4(1):52–58. find
  16. Sebastian Ruder, Ivan Vulić, and Anders Søgaard. 2019. A survey of cross-lingual word embedding models. Journal of Artificial Intelligence Research, 65:569–631. find
  17. Thamar Solorio and Yang Liu. 2008. Learning to predict code-switching points. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 973–981.
  18. Almeida Jacqueline Toribio. 2004. Convergence as an optimization strategy in bilingual speech: Evidence from code-switching. Bilingualism: Language and Cognition, 7(2):165–173. find
  19. Genta Indra Winata, Andrea Madotto, Chien-Sheng Wu, and Pascale Fung. 2018. Code-switching language modeling using syntax-aware multi-task learning. In Proceedings of the Third Workshop on Computational Approaches to Linguistic Code-Switching, pages 62– 67, Melbourne, Australia. Association for Comp… find
  20. Shuly Wintner, Safaa Shehadi, Yuli Zeira, Doreen Osmelak, and Yuval Nov. 2023. Shared lexical items as triggers of code switching. Transactions of the Association for Computational Linguistics, 11:1471– 1484. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tyagi-2026-modeling-cultural-subcultural-variation-code/