</> Code with Papers by Syntology

Datasets › MELD

MELD (Multimodal EmotionLines Dataset)

Introduced by Soujanya Poria et al. in MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations1 Jan 2019 archive 2025-07-28

Multimodal EmotionLines Dataset (MELD) has been created by enhancing and extending EmotionLines dataset. MELD contains the same dialogue instances available in EmotionLines, but it also encompasses audio and visual modality along with text. MELD has more than 1400 dialogues and 13000 utterances from Friends TV series. Multiple speakers participated in the dialogues. Each utterance in a dialogue has been labeled by any of these seven emotions -- Anger, Disgust, Sadness, Joy, Neutral, Surprise and Fear. MELD also has sentiment (positive, negative and neutral) annotation for each utterance.

Source: https://affective-meld.github.io/ Image Source: https://affective-meld.github.io/

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
Emotion Recognition in Conversation MELD ELR-GNN Weighted-F1 69.9 Efficient Long-distance Latent Relation-aware Graph... — 68 Compare
Multimodal Emotion Recognition MELD GraphSmile Weighted F1 66.71 Tracing Intricate Cues in Dialogue: Joint Graph... lijfrank-open/GraphSmile 3 Compare
Facial Expression Recognition MELD ConCluGen Weighted Accuracy 60.03 Multi-Task Multi-Modal Self-Supervised Learning for... tub-cv-group/conclugen 1 Compare

Papers archive 2025-07-28

30 shown of 62 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 289. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation 1 1 21 Jul 2025 not harvested
Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition 1 2 31 Jul 2024 not harvested
Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances 1 1 31 Jul 2024 not harvested
BiosERC: Integrating Biography Speakers Supported by LLMs for ERC Tasks 1 1 5 Jul 2024 not harvested
Efficient Long-distance Latent Relation-aware Graph Neural Network for Multi-modal Emotion Recognition in Conversations 0 1 27 Jun 2024 not harvested
Revisiting Multimodal Emotion Recognition in Conversation from the Perspective of Graph Spectrum 0 1 27 Apr 2024 not harvested
Revisiting Multi-modal Emotion Learning with Broad State Space Models and Probability-guidance Fusion 0 1 27 Apr 2024 not harvested
Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition 1 2 16 Apr 2024 not harvested
Emotion-Anchored Contrastive Learning Framework for Emotion Recognition in Conversation 1 1 29 Mar 2024 not harvested
CKERC : Joint Large Language Models with Commonsense Knowledge for Emotion Recognition in Conversation 0 1 12 Mar 2024 not harvested
TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation 1 1 16 Jan 2024 not harvested
Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimodal Emotion Recognition 1 1 18 Nov 2023 not harvested
Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models 2 1 14 Nov 2023 ran 5 of 7 samples (2 unverified; 7 pointer-only for licence)
Accumulating Word Representations in Multi-level Context Integration for ERC Task 1 1 6 Nov 2023 not harvested
A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations 1 1 31 Oct 2023 not harvested
Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation 0 1 4 Oct 2023 not harvested
InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Models 1 1 21 Sep 2023 ran 3 of 3 samples (0 unverified; 3 pointer-only for licence)
Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition 0 1 8 Aug 2023 not harvested
CFN-ESA: A Cross-Modal Fusion Network with Emotion-Shift Awareness for Dialogue Emotion Recognition 1 1 28 Jul 2023 not harvested
A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion Recognition in Multi-party Conversations 1 1 1 Jul 2023 not harvested
Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations 1 2 2 Jun 2023 not harvested
Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention 1 1 29 Apr 2023 not harvested
HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition 0 2 14 Apr 2023 not harvested
EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation 1 1 20 Mar 2023 not harvested
UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition 1 1 21 Nov 2022 not harvested
Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation 1 1 17 Oct 2022 not harvested
GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction 1 1 26 Aug 2022 not harvested
GA2MIF: Graph and Attention Based Two-Stage Multi-Source Information Fusion for Conversational Emotion Detection 1 1 25 Jul 2022 not harvested
GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion Recognition 1 1 6 Jul 2022 not harvested
Static and Dynamic Speaker Modeling based on Graph Neural Network for Emotion Recognition in Conversation 0 1 1 Jul 2022 not harvested

The full list of 62 is in the JSON twin.

Dataset loaders archive 2025-07-28

No loader listed in the archive.

Tasks archive 2025-07-28

Speech Emotion RecognitionEmotion Recognition in ConversationFacial Expression RecognitionMultimodal Emotion Recognition

License archive 2025-07-28

Unknown

Modalities archive 2025-07-28

VideosTexts

Languages archive 2025-07-28

EnglishChineseRussian

Variants archive 2025-07-28

  • MELD

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections