# EmotionX-IDEA: Emotion BERT -- an Affectional Model for Conversation

arXiv: https://arxiv.org/abs/1908.06264 · HTML: https://mlsanity.com/paper/1908.06264/

## Key facts

- Cited by 13 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 17 Aug 2019.

## Built on by (most cited first, 13 of 13)

- [Deep Emotion Recognition in Textual Conversations: A Survey](https://mlsanity.com/paper/2211.09172/) (2022)
- [Using Knowledge-Embedded Attention to Augment Pre-trained Language Models for Fine-Grained Emotion Recognition](https://mlsanity.com/paper/2108.00194/) (2021)
- [ArmanEmo: A Persian Dataset for Text-based Emotion Detection](https://mlsanity.com/paper/2207.11808/) (2022)
- [A Survey of Personality, Persona, and Profile in Conversational Agents and Chatbots](https://mlsanity.com/paper/2401.00609/) (2023)
- [Cross Domain Emotion Recognition using Few Shot Knowledge Transfer](https://mlsanity.com/paper/2110.05021/) (2021)
- [Transformer-based Text Classification on Unified Bangla Multi-class Emotion Corpus](https://mlsanity.com/paper/2210.06405/) (2022)
- [Emotion Recognition and Generation: A Comprehensive Review of Face, Speech, and Text Modalities](https://mlsanity.com/paper/2502.06803/) (2025)
- [Towards a Sentiment-Aware Conversational Agent](https://mlsanity.com/paper/2207.11774/) (2022)
- [Towards Generating Robust, Fair, and Emotion-Aware Explanations for Recommender Systems](https://mlsanity.com/paper/2208.08017/) (2022)
- [Context Unlocks Emotions: Text-based Emotion Classification Dataset Auditing with Large Language Models](https://mlsanity.com/paper/2311.03551/) (2023)
- ["That's so cute!": The CARE Dataset for Affective Response Detection](https://mlsanity.com/paper/2201.11895/) (2022)
- [Causal Categorization of Mental Health Posts using Transformers](https://mlsanity.com/paper/2301.02589/) (2023)
- [Social Convos: Capturing Agendas and Emotions on Social Media](https://mlsanity.com/paper/2402.15571/) (2024)

## Abstract (arXiv)

In this paper, we investigate the emotion recognition ability of the pre-training language model, namely BERT. By the nature of the framework of BERT, a two-sentence structure, we adapt BERT to continues dialogue emotion prediction tasks, which rely heavily on the sentence-level context-aware understanding. The experiments show that by mapping the continues dialogue into a causal utterance pair, which is constructed by the utterance and the reply utterance, models can better capture the emotions of the reply utterance. The present method has achieved 0.815 and 0.885 micro F1 score in the testing dataset of Friends and EmotionPush, respectively.