MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations

Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Gautam Naik, Erik Cambria +1 more
10/5/2018
cs.CL

Official code: declare-lab/MELD (1,094 stars, GPL-3.0, last commit 2026-05-17).

Abstract

Emotion recognition in conversations is a challenging task that has recently gained popularity due to its potential applications. Until now, however, a large-scale multimodal multi-party emotional conversational database containing more than two speakers per dialogue was missing. Thus, we propose the Multimodal EmotionLines Dataset (MELD), an extension and enhancement of EmotionLines. MELD contains about 13,000 utterances from 1,433 dialogues from the TV-series Friends. Each utterance is annotated with emotion and sentiment labels, and encompasses audio, visual and textual modalities. We propose several strong multimodal baselines and show the importance of contextual and multimodal information for emotion recognition in conversations. The full dataset is available for use at http:// affective-meld.github.io.

View on arXivView PDF

Code Implementations(1)

declare-lab/MELDOfficial100%
GPL-3.0

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation

1,094235PythonSep 29, 20185 months agoGPL-3.0
chatbotconversational-aidialoguedialogue-systemsemotion+9 more

Similar Papers

CFN-ESA: A Cross-Modal Fusion Network with Emotion-Shift Awareness for Dialogue Emotion Recognition

88% match1 repo172023

Multiscale Contextual Learning for Speech Emotion Recognition in Emergency Call Center Conversations

88% match2023

DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition

88% match1 repo472020

Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospects

87% match2025

TSAM: A Two-Stream Attention Model for Causal Emotion Entailment

87% match1 repo282022

DER-GCN: Dialogue and Event Relation-Aware Graph Convolutional Neural Network for Multimodal Dialogue Emotion Recognition

86% match2023

Cite this paper

@article{poria2018meld,
  title  = {MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations},
  author = {Soujanya Poria and Devamanyu Hazarika and Navonil Majumder and Gautam Naik and Erik Cambria and Rada Mihalcea},
  year   = {2018},
  eprint = {1810.02508},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1810.02508}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1810.02508.svg)](https://codeofpaper.com/paper/1810.02508)

Discussion