# Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training

arXiv: https://arxiv.org/abs/1809.04505 · HTML: https://mlsanity.com/paper/1809.04505/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2018.

## Built on by (most cited first, 11 of 11)

- [Towards Interactive Intelligence for Digital Humans](https://mlsanity.com/paper/2512.13674/) (2025)
- [Multi-Task Learning and Adapted Knowledge Models for Emotion-Cause Extraction](https://mlsanity.com/paper/2106.09790/) (2021)
- [EmpBot: A T5-based Empathetic Chatbot focusing on Sentiments](https://mlsanity.com/paper/2111.00310/) (2021)
- [Efficient Emotion-Aware Iconic Gesture Prediction for Robot Co-Speech](https://mlsanity.com/paper/2604.11417/) (2026)
- [Sentiment analysis in tweets: an assessment study from classical to modern text representation models](https://mlsanity.com/paper/2105.14373/) (2021)
- [ViDove: A Translation Agent System with Multimodal Context and Memory-Augmented Reasoning](https://mlsanity.com/paper/2507.07306/) (2025)
- [Block-Segmentation Vectors for Arousal Prediction using Semi-supervised Learning](https://mlsanity.com/paper/2204.05096/) (2022)
- [A Unified Spoken Language Model with Injected Emotional-Attribution Thinking for Human-like Interaction](https://mlsanity.com/paper/2601.04960/) (2026)
- [Taming the Beast: Learning to Control Neural Conversational Models](https://mlsanity.com/paper/2108.10561/) (2021)
- [Emotion Embeddings unicodex2014 Learning Stable and Homogeneous Abstractions from Heterogeneous Affective Datasets](https://mlsanity.com/paper/2308.07871/) (2023)
- [A Primer on Computational Semantics for Artificial Intelligence Systems](https://mlsanity.com/paper/2608.25022/) (2026)

## Abstract (arXiv)

In this paper, we propose Emo2Vec which encodes emotional semantics into vectors. We train Emo2Vec by multi-task learning six different emotion-related tasks, including emotion/sentiment analysis, sarcasm classification, stress detection, abusive language classification, insult detection, and personality recognition. Our evaluation of Emo2Vec shows that it outperforms existing affect-related representations, such as Sentiment-Specific Word Embedding and DeepMoji embeddings with much smaller training corpora. When concatenated with GloVe, Emo2Vec achieves competitive performances to state-of-the-art results on several tasks using a simple logistic regression classifier.