TY - GEN A1 - Reelfs, Jens Helge A1 - Hohlfeld, Oliver A1 - Strohmaier, Markus A1 - Henckell, Niklas T1 - Word-Emoji embeddings from large scale messaging data reflect real world semantic associations of expressive icons T2 - Conference: ICWSM Workshop on Emoji Understanding and Applications in Social Media 2020 N2 - We train word-emoji embeddings on large scale messagingdata obtained from the Jodel online social network. Our dataset contains more than 40 million sentences, of which 11 million sentences are annotated with a subset of the Unicode13.0 standard Emoji list. We explore semantic emoji associations contained in this embedding by analyzing associations between emojis, between emojis and text, and betweentext and emojis. Our investigations demonstrate anecdotallythat word-emoji embeddings trained on large scale messaging data can reflect real-world semantic associations. To enable further research we release the Jodel Emoji EmbeddingDataset (JEED1488) containing 1488 emojis and their embeddings along 300 dimensions. Y1 - 2020 UR - http://workshop-proceedings.icwsm.org/pdf/2020_02.pdf ER -