Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm

Abstract

NLP tasks are often limited by scarcity of manually annotated data. In social media sentiment analysis and related tasks, researchers have therefore used binarized emoticons and specific hashtags as forms of distant supervision. Our paper shows that by extending the distant supervision to a more diverse set of noisy labels, the models can learn richer representations. Through emoji prediction on a dataset of 1246 million tweets containing one of 64 common emojis we obtain state-of-the-art performance on 8 benchmark datasets within sentiment, emotion and sarcasm detection using a single pretrained model. Our analyses confirm that the diversity of our emotional labels yield a performance improvement over previous distant supervision approaches.

Accepted at EMNLP 2017. Please include EMNLP in any citations. Minor changes from the EMNLP camera-ready version. 9 pages + references and supplementary material

Cited by in corpus (15)

• Twitter Sentiment Analysis via Bi-sense Emoji Embedding and Attention-based LSTM
• Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunities
• SEntiMoji: An Emoji-Powered Learning Approach for Sentiment Analysis in Software Engineering
• Multimodal Emotion Classification
• Improved Biomedical Word Embeddings in the Transformer Era
• Embodying Pre-Trained Word Embeddings Through Robot Actions
• Every Colour You Are: Stance Prediction and Turnaround in Controversial Issues
• Improving Sentiment Analysis with Multi-task Learning of Negation
• Emotion helps Sentiment: A Multi-task Model for Sentiment and Emotion Analysis
• EvoMSA: A Multilingual Evolutionary Approach for Sentiment Analysis
• From Theories on Styles to their Transfer in Text: Bridging the Gap with a Hierarchical Survey
• Learning Bidirectional Translation between Descriptions and Actions with Small Paired Data
• Multi-Label Sentiment Analysis on 100 Languages with Dynamic Weighting for Label Imbalance
• VoiceMoji: A Novel On-Device Pipeline for Seamless Emoji Insertion in Dictation
• A Deep Neural Framework for Contextual Affect Detection