Detecting harm in context: toxicity, politeness, and cultural pragmatics in Indonesian social media NLP

M. Rifa Jamaludin Nasir

doi:10.67490/ijcl.v1i3.1028

Authors

M. Rifa Jamaludin Nasir Universitas Islam Negeri Salatiga Author

DOI:

https://doi.org/10.67490/ijcl.v1i3.1028

Keywords:

Annotation uncertainty, Cultural pragmatics, Indonesian NLP, Politeness, Toxicity detection

Abstract

Background: Indonesian social media toxicity detection remains difficult because harmful meaning is often produced through profanity, indirectness, ridicule, code-mixing, identity reference, and culturally situated politeness rather than through abusive vocabulary alone. Objective: This study examines how toxicity, politeness, and cultural pragmatics interact in Indonesian social media NLP annotation and asks what contextual evidence is required to distinguish abuse, hate speech, satire, criticism, and banter. Method: Using 60 anonymised Indonesian Twitter/X items from a public multi-label hate speech and abusive-language corpus, this study applies a mixed computational-pragmatic design combining source labels with manual interpretation of target, severity, facework, contextual validation, and risk. Results: Findings show that toxicity classes are evenly distributed, but target, domain, and severity differentiate surface abuse from identity-targeted harm. Facework cues such as direct address, laughter, ridicule, and abusive labels appear unevenly across toxicity classes, demonstrating that politeness and impoliteness cannot be inferred from lexical toxicity. Cultural-pragmatic coding shows that religion, ethnicity, gender, platform traces, political indexing, and local-language ambiguity require contextual validation before model outputs can be treated as reliable. Implication: Indonesian NLP moderation should combine classification with pragmatic annotation. Novelty: This study reframes toxicity detection as culturally grounded, target-aware, and pragmatically validated harm interpretation.

References

[1] DataReportal, Digital 2026: Indonesia, Nov. 5, 2025. [Online]. Available: https://datareportal.com/reports/digital-2026-indonesia.

[2] J. Santoso, "Indonesian named entity recognition using BiLSTM-CRF with domain-specific word embeddings," Indonesian Journal of Computational Language Studies, vol. 1, no. 1, pp. 1-10, 2026.

[3] W. Novitasari, "Sentiment analysis on Indonesian political discourse using transformer-based models," Indonesian Journal of Computational Language Studies, vol. 1, no. 1, pp. 11-21, 2026.

[4] A. Nugroho, "Code-mixing detection in Indonesian-English tweets using machine learning and linguistic features," Indonesian Journal of Computational Language Studies, vol. 1, no. 1, pp. 22-31, 2026.

[5] A. Wahid, "Lexical patterns in Indonesian academic writing: A corpus-based analysis for writing assistance," Indonesian Journal of Computational Language Studies, vol. 1, no. 1, pp. 32-42, 2026.

[6] T. Yuliyana, "Automatic readability assessment of Indonesian educational texts using hybrid NLP approaches," Indonesian Journal of Computational Language Studies, vol. 1, no. 1, pp. 43-52, 2026.

[7] M. I. Ibrahim, "Morphological segmentation of low-resource Indonesian dialects using unsupervised neural models," Indonesian Journal of Computational Language Studies, vol. 1, no. 1, pp. 53-62, 2026.

[8] A. E. Bouazzaoui, "Beyond translated benchmarks: A culturally grounded evaluation of large language models for Indonesian language understanding," Indonesian Journal of Computational Language Studies, vol. 1, no. 2, 2026.

[9] F. D. Wulandari, "Do large language models reason consistently across Indonesian languages? A multilingual evaluation of Indonesian, Javanese, Sundanese, and Buginese," Indonesian Journal of Computational Language Studies, vol. 1, no. 2, 2026.

[10] Nadiyah, "When safety fails in local languages: Evaluating culturally sensitive responses of large language models in multilingual Indonesia," Indonesian Journal of Computational Language Studies, vol. 1, no. 2, 2026.

[11] R. T. Wibisono, "Hallucinating the archipelago: Detecting factual and cultural errors in retrieval-augmented generation for Indonesian knowledge," Indonesian Journal of Computational Language Studies, vol. 1, no. 2, 2026.

[12] M. A. Sumadi, "Who gets represented by Indonesian AI? Measuring regional, gender, and sociolinguistic bias in large language models," Indonesian Journal of Computational Language Studies, vol. 1, no. 2, 2026.

[13] A. Hadziqi, "Small models, many languages: Parameter-efficient adaptation of multilingual language models for low-resource Indonesian languages," Indonesian Journal of Computational Language Studies, vol. 1, no. 2, 2026.

[14] J. L. Austin, How to Do Things with Words. Oxford, U.K.: Oxford Univ. Press, 1962.

[15] J. R. Searle, Speech Acts: An Essay in the Philosophy of Language. Cambridge, U.K.: Cambridge Univ. Press, 1969.

[16] P. Brown and S. C. Levinson, Politeness: Some Universals in Language Usage. Cambridge, U.K.: Cambridge Univ. Press, 1987.

[17] M. A. Locher and R. J. Watts, "Politeness theory and relational work," Journal of Politeness Research, vol. 1, no. 1, pp. 9-33, 2005.

[18] H. Spencer-Oatey, "Face, im/politeness and rapport," in Culturally Speaking: Culture, Communication and Politeness Theory, 2nd ed., H. Spencer-Oatey, Ed. London: Continuum, 2008, pp. 11-47.

[19] J. Culpeper, "Towards an anatomy of impoliteness," Journal of Pragmatics, vol. 25, no. 3, pp. 349-367, 1996.

[20] J. Culpeper, Impoliteness: Using Language to Cause Offence. Cambridge, U.K.: Cambridge Univ. Press, 2011.

[21] H. P. Grice, "Logic and conversation," in Syntax and Semantics: Speech Acts, vol. 3, P. Cole and J. L. Morgan, Eds. New York: Academic Press, 1975, pp. 41-58.

[22] M. Haugh, "Im/politeness, social practice and participation order," Journal of Pragmatics, vol. 58, pp. 52-72, 2013.

[23] M. O. Ibrohim and I. Budi, "Multi-label hate speech and abusive language detection in Indonesian Twitter," in Proc. 3rd Workshop on Abusive Language Online, 2019, pp. 46-57, doi: 10.18653/v1/W19-3506.