Emojinize: Enriching Any Text with Emoji Translations (2403.03857v2)
Abstract: Emoji have become ubiquitous in written communication, on the Web and beyond. They can emphasize or clarify emotions, add details to conversations, or simply serve decorative purposes. This casual use, however, barely scratches the surface of the expressive power of emoji. To further unleash this power, we present Emojinize, a method for translating arbitrary text phrases into sequences of one or more emoji without requiring human input. By leveraging the power of LLMs, Emojinize can choose appropriate emoji by disambiguating based on context (eg, cricket-bat vs bat) and can express complex concepts compositionally by combining multiple emoji (eq, "Emojinize" is translated to input-latin-letters right-arrow grinning-face). In a cloze test--based user study, we show that Emojinize's emoji translations increase the human guessability of masked words by 55%, whereas human-picked emoji translations do so by only 29%. These results suggest that emoji provide a sufficiently rich vocabulary to accurately translate a wide variety of words. Moreover, annotating words and phrases with Emojinize's emoji translations opens the door to numerous downstream applications, including children learning how to read, adults learning foreign languages, and text understanding for people with learning disabilities.
- Alshenqeeti and Hamza. 2016. Are Emojis Creating a New or Old Visual Language for New Generations? A Socio-semiotic Study. https://papers.ssrn.com/abstract=3709343
- Federated Learning for Emoji Prediction in a Mobile Keyboard. https://arxiv.org/abs/1906.04329
- BIG bench authors. 2023. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models. Transactions on Machine Learning Research (2023). https://openreview.net/forum?id=uyTL5Bvosj
- Fred Benenson. 2021. Emoji Dick. http://www.emojidick.com/
- Language models are few-shot learners. Advances in neural information processing systems 33 (2020), 1877–1901.
- Alex Clark. 2014. Emoji: the first truly global language? | Mobile phones | The Guardian. https://www.theguardian.com/technology/2014/aug/31/emoji-became-first-global-language
- On the Context-Free Ambiguity of Emoji. Proceedings of the International AAAI Conference on Web and Social Media 16 (May 2022), 1388–1392. https://doi.org/10.1609/icwsm.v16i1.19393
- To emoji or not to emoji? Examining the influence of emoji on consumer reactions to advertising. Journal of Business Research 96 (March 2019), 147–156. https://doi.org/10.1016/j.jbusres.2018.11.007
- Timothy Drobnick. 2023. Ghostly Guardian by Timothy L. Drobnick Sr. - Free eBook. https://manybooks.net/titles/ghostly-guardian
- emoji2vec: Learning emoji representations from their description. arXiv preprint arXiv:1609.08359 (2016).
- Emojipedia. 2023. Emoji Statistics. https://emojipedia.org/stats. [Online; accessed 17-Aug-2023].
- Mark Farnum. 2023. Emojipasta Generator. https://emojify.net/
- Johnny Firic. 2023. The Oldest Word by Johnny Firic - Free eBook. https://manybooks.net/titles/the-oldest-word
- Jing Ge and Ulrike Gretzel. 2018. Emoji rhetoric: a social media influencer perspective. Journal of Marketing Management 34, 15-16 (Oct. 2018), 1272–1295. https://doi.org/10.1080/0267257X.2018.1483960 Publisher: Routledge _eprint: https://doi.org/10.1080/0267257X.2018.1483960.
- Google. 2023. Google News. https://news.google.com
- Muhammad Hasyim. 2019. Linguistic functions of emoji in social media communication. Opcion 35 (2019).
- spaCy: Industrial-strength natural language processing in python. (2020).
- Flows: Building Blocks of Reasoning and Collaborating AI. https://arxiv.org/abs/2308.01285v1
- Alex Kirk. 2023. Paycheck to Paycheck by Kirk Alex - Free eBook. https://manybooks.net/titles/paycheck-to-paycheck
- Gerald Knight. 2023. The Legend Is Born by Gerald Knight - Free eBook. https://manybooks.net/titles/the-legend-is-born
- Venkata Ravi Kiran Kolla. 2021. Emojify: A Deep Learning Approach for Custom Emoji Creation and Recognition. https://papers.ssrn.com/abstract=4413719
- Learning from the ubiquitous language: an empirical analysis of emoji usage of smartphone users. In Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp ’16). Association for Computing Machinery, New York, NY, USA, 770–780. https://doi.org/10.1145/2971648.2971724
- Gretchen MCCulloch. 2019. Children Are Using Emoji for Digital-Age Language Learning | WIRED. https://www.wired.com/story/children-emoji-language-learning/
- Understanding Emoji Ambiguity in Context: The Role of Text in Emoji-Related Miscommunication. Proceedings of the International AAAI Conference on Web and Social Media 11, 1 (May 2017), 152–161. https://doi.org/10.1609/icwsm.v11i1.14901 Number: 1.
- “Blissfully Happy” or “Ready toFight”: Varying Interpretations of Emoji. Proceedings of the International AAAI Conference on Web and Social Media 10, 1 (2016), 259–268. https://doi.org/10.1609/icwsm.v10i1.14757 Number: 1.
- OpenAI. 2023a. GPT-4 Technical Report. https://doi.org/10.48550/arXiv.2303.08774 arXiv:2303.08774 [cs].
- OpenAI. 2023b. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL]
- Beyond Just Text: Semantic Emoji Similarity Modeling to Support Expressive Communication. ACM Transactions on Computer-Human Interaction 24, 1 (March 2017), 6:1–6:42. https://doi.org/10.1145/3039685
- Jordan Stockill. 2020. How emojis can help you learn a new language | by Jordan Stockill | UX Collective. https://uxdesign.cc/how-emojis-can-help-you-learn-a-new-language-ed159b94ef7d
- Ying Tang and Khe Foon Hew. 2019. Emoticon, Emoji, and Sticker Use in Computer-Mediated Communication: A Review of Theories and Research Findings. International Journal of Communication 13, 0 (May 2019), 27. https://ijoc.org/index.php/ijoc/article/view/10966 Number: 0.
- AutoGPT Team. 2023. AutoGPT. https://github.com/Significant-Gravitas/Auto-GPT.
- Tess Thompson. 2023. The Making of a Matchmaker by Tess Thompson - Free eBook. https://manybooks.net/titles/the-making-of-a-matchmaker
- Garreth W. Tigwell and David R. Flatla. 2016. Oh that’s what you meant! reducing emoji misunderstanding. In Proceedings of the 18th International Conference on Human-Computer Interaction with Mobile Devices and Services Adjunct (MobileHCI ’16). Association for Computing Machinery, New York, NY, USA, 859–866. https://doi.org/10.1145/2957265.2961844
- Llama 2: Open Foundation and Fine-Tuned Chat Models. https://doi.org/10.48550/arXiv.2307.09288 arXiv:2307.09288 [cs].
- Attention Is All You Need. https://doi.org/10.48550/arXiv.1706.03762 arXiv:1706.03762 [cs].
- Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems 35 (2022), 24824–24837.
- EmojiNet: An Open Service and API for Emoji Sense Discovery. Proceedings of the International AAAI Conference on Web and Social Media 11, 1 (May 2017), 437–446. https://doi.org/10.1609/icwsm.v11i1.14857 Number: 1.
- A Semantics-Based Measure of Emoji Similarity. In Proceedings of the International Conference on Web Intelligence (Leipzig, Germany) (WI ’17). Association for Computing Machinery, New York, NY, USA, 646–653. https://doi.org/10.1145/3106426.3106490
- Taehoon Kim Wurster, Kevin. 2023. emoji: Emoji for Python. https://github.com/carpedm20/emoji/
- Goodbye Text, Hello Emoji: Mobile Communication on WeChat in China. In Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems (CHI ’17). Association for Computing Machinery, New York, NY, USA, 748–759. https://doi.org/10.1145/3025453.3025800