emoji2vec: Learning Emoji Representations from their Description

By Ben Eisner, Tim Rocktaschel, Isabelle Augenstein, Matko Bosnjak, Sebastian Riedel. SocialNLP@EMNLP, 2016

305 citations recorded by the source corpus.

Many current natural language processing applications for social media rely on representation learning and utilize pre-trained word embeddings. There currently exist several publicly-available, pre-trained sets of word embeddings, but they contain few or no emoji representations even as emoji usage in social media has increased. In this paper we release emoji2vec, pre-trained embeddings for all Unicode emoji which are learned from their description in the Unicode emoji standard. The resulting emoji embeddings can be readily used in downstream social natural language processing applications alongside word2vec. We demonstrate, for the downstream task of sentiment analysis, that emoji embeddings learned from short descriptions outperforms a skip-gram model trained on a large collection of tweets, while avoiding the need for contexts in which emoji need to appear frequently in order to estimate a representation.

Subfields: Artificial Intelligence, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/60140406ec6990d7d82fea14730a60609a9009c0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Human-Computer Interaction

Citations in the corpus

Sentiment Analysis: Detecting Valence, Emotions, and Other Affectual States from Text (2016, background): “They show that using features from 500 emotion categories significantly improved performance over using features from just the Ekman emotions. Pool and Nissim (2016) collected public Facebook posts and their associated user-marked emotion reaction data from news and entertainment companies to develo”
SemEval-2019 Task 3: EmoContext Contextual Emotion Detection in Text (2019, methodology): “Partici-pant teams tried various ways to encode the emotional content expressed by emoticons, and Deep-moji and Emoji2Vec (Eisner et al., 2016) were utilized in this regard.”
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation (2021, background): “Given the ubiquitousness of emojis, there is a growing body of work researching the linguistic and cultural aspects of emojis (Guntuku et al., 2019) and how we can leverage the use of emojis to help solve NLP tasks (Eisner et al., 2016).”
How Gender and Skin Tone Modifiers Affect Emoji Semantics in Twitter (2018, methodology): “While there have been approaches attempting to model emojis with distributional semantics (Aoki and Uchida, 2011; Barbieri et al., 2016; Eisner et al., 2016; Ljubešic and Fišer, 2016; Wijeratne et al., 2017), to the best of our knowledge this is the first work that semantically analyzes modifiers…”
Procedural Content Generation via Machine Learning (PCGML) (2017, background): “These vectors are then used for analogical reasoning [75] or for generation [76], but have yet to see use in the generation of game content.”
SemEval 2018 Task 2: Multilingual Emoji Prediction (2018, methodology): “Contributions in this respect include models trained on Twitter data (Barbieri et al., 2016c), Twitter data together with the ofﬁcial unicode description (Eisner et al., 2016), or using text from a popular keyboard app Ai et al. (2017).”
Multi-Task Learning of Pairwise Sequence Classification Tasks over Disparate Label Spaces (2018, background): “, 2017), sentiment correlates with emotion (Felbo et al., 2017; Eisner et al., 2016), etc.”
Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm (2017, background): “Another way of automatically interpreting the emotional content of an emoji is to learn emoji embeddings from the words describing the emoji-semantics in ofﬁcial emoji tables (Eisner et al., 2016).”