{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/emoji2vec-learning-emoji-representations-from","title":"emoji2vec: Learning Emoji Representations from their Description","arxiv_id":"1609.08359","date":"2016-09-27","proceeding":"WS 2016 11","authors":["Ben Eisner","Tim Rocktäschel","Isabelle Augenstein","Matko Bošnjak","Sebastian Riedel"],"abstract":"Many current natural language processing applications for social media rely\non representation learning and utilize pre-trained word embeddings. There\ncurrently exist several publicly-available, pre-trained sets of word\nembeddings, but they contain few or no emoji representations even as emoji\nusage in social media has increased. In this paper we release emoji2vec,\npre-trained embeddings for all Unicode emoji which are learned from their\ndescription in the Unicode emoji standard. The resulting emoji embeddings can\nbe readily used in downstream social natural language processing applications\nalongside word2vec. We demonstrate, for the downstream task of sentiment\nanalysis, that emoji embeddings learned from short descriptions outperforms a\nskip-gram model trained on a large collection of tweets, while avoiding the\nneed for contexts in which emoji need to appear frequently in order to estimate\na representation.","url_abs":"http://arxiv.org/abs/1609.08359v2","url_pdf":"http://arxiv.org/pdf/1609.08359v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"emoji2vec-learning-emoji-representations-from","repo_url":"https://github.com/uclmr/emoji2vec","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"emoji2vec-learning-emoji-representations-from","repo_url":"https://github.com/hougrammer/emoji_project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"emoji2vec-learning-emoji-representations-from","repo_url":"https://github.com/joonasrooben/NLP-text2emoji","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"emoji2vec-learning-emoji-representations-from","repo_url":"https://github.com/pwiercinski/emoji2vec_pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"emoji2vec-learning-emoji-representations-from","repo_url":"https://github.com/qq345736500/sarcasm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"emoji2vec-learning-emoji-representations-from","repo_url":"https://github.com/uclnlp/emoji2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"emoji2vec-learning-emoji-representations-from","repo_url":"https://github.com/yagudinamir/emoji","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.08359","atlas_url":"https://app.syntology.ai/?focus=1609.08359","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}