Unmasking Mnemonics – Leveraging Content Moderation Model for Decoding Encoded Communication in Digital Conversations

Unmasking Mnemonics – Leveraging Content Moderation Model for Decoding Encoded Communication in Digital Conversations Sumithra S School of Computing Sciences, Vels Institute of Science, Technology and Advanced Studies, Pallavaram, Chennai, Tamil Nadu, India. Sujatha P Department of Computer Applications, Vels Institute of Science, Technology and Advanced Studies, Pallavaram, Chennai, Tamil Nadu, India.

In today’s world, digital platforms have witnessed an explosion in the digital conversations and are not straightforward. A significant contributor to this complexity is the use of subtle references to another context or with encoded texts. These are said to be Mnemonics appearing in the form of Abbreviations, Numeronymns, Symbolic representations, Emoji-based codes, Leetspeak etc.., in everyday communication. There are various types of mnemonics used in online conversations, which include phonetic substitutions (eg. Gr8 for ‘great’), numerical encoding (e.g., 143 for ‘I love you’), and symbolic representations (with emojis and icons), abbreviations (“LOL” for Laugh Out Loud) etc., This linguistic creativity is not only a tool for memory and efficiency, but also a growing challenge for automated moderation and content understanding systems, as mnemonics often encode non-explicit, sensitive, or policy-relevant meanings that typical keyword-based approaches might fail to identify. To address this gap, we introduce a Content Moderation Model, which is a large language model (LLM) based pipeline that systematically detects, categorizes, and deciphers both general and context-specific mnemonic constructs within user-generated text. This methodology builds upon advances in deep learning, leveraging the representational power and semantic flexibility of models such as GPT-4.1, known for their success in complex linguistic and content analysis tasks across domains. This framework uses a corpus of both harmless and sexually-coded user-generated texts to identify mnemonic patterns such as Phonetic substitutions, Emoji usage, and Leetspeak. The system accurately flags and classifies mnemonic types, enabling improved moderation, linguistic analysis, and platform policy design. The outcomes—quantified through rigorous empirical validation, demonstrates substantial improvements in identifying and decoding diverse mnemonic forms. These findings provide actionable insights for platform policy, and the design of more accessible, inclusive communication systems that acknowledge both the benefits and risks of mnemonic language.
10 5 2025 10 5 2025 2292 2304 10.53759/7669/jmc202505178 10.53759/7669/jmc202505178 https://anapub.co.ke/journals/jmc/jmc_abstract/2025/jmc_volume_05_issue_04/jmc_volume5_issue4_178.html https://anapub.co.ke/journals/jmc/jmc_pdf/2025/jmc_volume_5-issue_4/JMC202505178.pdf 10.1111/tops.12369 C. B. Stone and Q. Wang, “From Conversations to Digital Communication: The Mnemonic Consequences of Consuming and Producing Information via Social Media,” Topics in Cognitive Science, vol. 11, no. 4, pp. 774–793, Jul. 2018, doi: 10.1111/tops.12369. 10.18653/v1/2024.findings-emnlp.316 J. Lee, H. McNichols, and A. Lan, “Exploring Automated Keyword Mnemonics Generation with Large Language Models via Overgenerate-and-Rank,” Findings of the Association for Computational Linguistics: EMNLP 2024, pp. 5521–5542, 2024, doi: 10.18653/v1/2024.findings-emnlp.316. 10.1037//0278-7393.6.5.558 H. L. Roediger, “The effectiveness of four mnemonics in ordering recall.,” Journal of Experimental Psychology: Human Learning & Memory, vol. 6, no. 5, pp. 558–567, 1980, doi: 10.1037//0278-7393.6.5.558. Gupta, Aditi & Kumaraguru, Ponnurangam & Sureka, Ashish. “Characterizing Pedophile Conversations on the Internet using Online Grooming”, 2012. Sesar, Kristina & Dodaj, Arta, “Sexting and emotional regulation strategies among young adults,” 2019, 10.6092/2282-1619/2019.7.2008. 10.1017/cbo9781139524643.015 J. Hulstijn, “Mnemonic methods in foreign language vocabulary learning: Theoretical considerations and pedagogical implications,” Second Language Vocabulary Acquisition, pp. 203–224, Dec. 1996, doi: 10.1017/cbo9781139524643.015. 10.1017/mem.2024.7 R.-J. Adriaansen, “Latent and explicit mnemonic communities on social media: studying digital memory formation through hashtag co-occurrence analysis,” Memory, Mind & Media, vol. 3, 2024, doi: 10.1017/mem.2024.7. 10.1002/cb.2210 S. Mookherjee, S. Mohanty, and S. Mukherjee, “Affinity to mnemonic features of social media: Antecedent and consequences,” Journal of Consumer Behaviour, vol. 22, no. 6, pp. 1330–1347, Jul. 2023, doi: 10.1002/cb.2210. 10.1007/978-3-658-41276-0 A. L. Migowski da Silva, Mnemonic Practices on Social Media. Springer Fachmedien Wiesbaden, 2023. doi: 10.1007/978-3-658-41276-0. 10.3758/s13421-012-0202-8 S. J. Barber and M. Mather, “Forgetting in context: The effects of age, emotion, and social factors on retrieval-induced forgetting,” Memory & Cognition, vol. 40, no. 6, pp. 874–888, Mar. 2012, doi: 10.3758/s13421-012-0202-8. 10.52589/ajsshr-iwuy1dys O. A. V., U. A. O., and A. C. C., “Encoding and Decoding of Emoji on Social Media for Expression Sharing among University Students in Anambra State,” African Journal of Social Sciences and Humanities Research, vol. 8, no. 1, pp. 24–35, Jan. 2025, doi: 10.52589/ajsshr-iwuy1dys. S. Sumithra, Dr. P. Sujatha, “Evolution of Adult Content Detection,” In the International Conference on Information and Business Intelligence (ICIBI – 2024), Organized by Saveetha College of Liberal Arts & Sciences held on 15th Feb 2024.