{"url":"/dataset/meld","name":"MELD","full_name":"Multimodal EmotionLines Dataset","description_markdown":"**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.\r\n\r\nSource: [https://affective-meld.github.io/](https://affective-meld.github.io/)\r\nImage Source: [https://affective-meld.github.io/](https://affective-meld.github.io/)","description_withheld":null,"homepage":"https://affective-meld.github.io/","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/meld-a-multimodal-multi-party-dataset-for","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","first_author":"Soujanya Poria","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Speech Emotion Recognition","url":"/task/speech-emotion-recognition","datasets_with_task":"/datasets/task/speech-emotion-recognition"},{"name":"Emotion Recognition in Conversation","url":"/task/emotion-recognition-in-conversation","datasets_with_task":"/datasets/task/emotion-recognition-in-conversation"},{"name":"Facial Expression Recognition","url":"/task/facial-expression-recognition-1","datasets_with_task":"/datasets/task/facial-expression-recognition-1"},{"name":"Multimodal Emotion Recognition","url":"/task/multimodal-emotion-recognition","datasets_with_task":"/datasets/task/multimodal-emotion-recognition"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Russian","url":"/datasets/language/russian"}],"variants":["MELD"],"data_loaders":[],"num_papers_in_archive":289,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/emotion-recognition-in-conversation-on-meld","task":"Emotion Recognition in Conversation","dataset_variant":"MELD","rows":68,"metrics":["Weighted-F1","Accuracy","Micro-F1","Balanced Accuracy"],"first_row_in_archive_order":{"model":"ELR-GNN","paper":"/paper/efficient-long-distance-latent-relation-aware","metrics":{"Accuracy":"68.7","Weighted-F1":"69.9"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multimodal-emotion-recognition-on-meld","task":"Multimodal Emotion Recognition","dataset_variant":"MELD","rows":3,"metrics":["Weighted F1","Accuracy"],"first_row_in_archive_order":{"model":"GraphSmile","paper":"/paper/2407-21536","metrics":{"Accuracy":"67.70","Weighted F1":"66.71"},"code_links":[{"title":"lijfrank-open/GraphSmile","url":"https://github.com/lijfrank-open/GraphSmile"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/facial-expression-recognition-on-meld","task":"Facial Expression Recognition","dataset_variant":"MELD","rows":1,"metrics":["Weighted Accuracy"],"first_row_in_archive_order":{"model":"ConCluGen","paper":"/paper/multi-task-multi-modal-self-supervised","metrics":{"Weighted Accuracy":"60.03"},"code_links":[{"title":"tub-cv-group/conclugen","url":"https://github.com/tub-cv-group/conclugen"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/long-short-distance-graph-neural-networks-and","title":"Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation","date":"2025-07-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/2407-21536","title":"Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition","date":"2024-07-31","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/2407-21315","title":"Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances","date":"2024-07-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bioserc-integrating-biography-speakers","title":"BiosERC: Integrating Biography Speakers Supported by LLMs for ERC Tasks","date":"2024-07-05","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/efficient-long-distance-latent-relation-aware","title":"Efficient Long-distance Latent Relation-aware Graph Neural Network for Multi-modal Emotion Recognition in Conversations","date":"2024-06-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/revisiting-multimodal-emotion-recognition-in","title":"Revisiting Multimodal Emotion Recognition in Conversation from the Perspective of Graph Spectrum","date":"2024-04-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/revisiting-multi-modal-emotion-learning-with","title":"Revisiting Multi-modal Emotion Learning with Broad State Space Models and Probability-guidance Fusion","date":"2024-04-27","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/multi-task-multi-modal-self-supervised","title":"Multi-Task Multi-Modal Self-Supervised Learning for Facial Expression Recognition","date":"2024-04-16","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/emotion-anchored-contrastive-learning","title":"Emotion-Anchored Contrastive Learning Framework for Emotion Recognition in Conversation","date":"2024-03-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ckerc-joint-large-language-models-with","title":"CKERC : Joint Large Language Models with Commonsense Knowledge for Emotion Recognition in Conversation","date":"2024-03-12","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/telme-teacher-leading-multimodal-fusion","title":"TelME: Teacher-leading Multimodal Fusion Network for Emotion Recognition in Conversation","date":"2024-01-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/joyful-joint-modality-fusion-and-graph","title":"Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimodal Emotion Recognition","date":"2023-11-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/qwen-audio-advancing-universal-audio","title":"Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models","date":"2023-11-14","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":5,"samples_unverified":2,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/accumulating-word-representations-in-multi","title":"Accumulating Word Representations in Multi-level Context Integration for ERC Task","date":"2023-11-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-transformer-based-model-with-self","title":"A Transformer-Based Model With Self-Distillation for Multimodal Emotion Recognition in Conversations","date":"2023-10-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multimodal-prompt-transformer-with-hybrid","title":"Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in Conversation","date":"2023-10-04","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/instructerc-reforming-emotion-recognition-in","title":"InstructERC: Reforming Emotion Recognition in Conversation with Multi-task Retrieval-Augmented Large Language Models","date":"2023-09-21","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/revisiting-disentanglement-and-fusion-on","title":"Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition","date":"2023-08-08","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cfn-esa-a-cross-modal-fusion-network-with","title":"CFN-ESA: A Cross-Modal Fusion Network with Emotion-Shift Awareness for Dialogue Emotion Recognition","date":"2023-07-28","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/a-facial-expression-aware-multimodal-multi","title":"A Facial Expression-Aware Multimodal Multi-task Learning Framework for Emotion Recognition in Multi-party Conversations","date":"2023-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/supervised-adversarial-contrastive-learning","title":"Supervised Adversarial Contrastive Learning for Emotion Recognition in Conversations","date":"2023-06-02","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/hierarchical-dialogue-understanding-with-1","title":"Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention","date":"2023-04-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/hcam-hierarchical-cross-attention-model-for","title":"HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition","date":"2023-04-14","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/emotionic-emotional-inertia-and-contagion","title":"EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation","date":"2023-03-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unimse-towards-unified-multimodal-sentiment","title":"UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition","date":"2022-11-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/supervised-prototypical-contrastive-learning","title":"Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation","date":"2022-10-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/grasp-guiding-model-with-relational-semantics","title":"GRASP: Guiding model with RelAtional Semantics using Prompt for Dialogue Relation Extraction","date":"2022-08-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ga2mif-graph-and-attention-based-two-stage","title":"GA2MIF: Graph and Attention Based Two-Stage Multi-Source Information Fusion for Conversational Emotion Detection","date":"2022-07-25","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/graphcfc-a-directed-graph-based-cross-modal","title":"GraphCFC: A Directed Graph Based Cross-Modal Feature Complementation Approach for Multimodal Conversational Emotion Recognition","date":"2022-07-06","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/static-and-dynamic-speaker-modeling-based-on","title":"Static and Dynamic Speaker Modeling based on Graph Neural Network for Emotion Recognition in Conversation","date":"2022-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/the-emotion-is-not-one-hot-encoding-learning","title":"The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation","date":"2022-06-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/m2fnet-multi-modal-fusion-network-for-emotion","title":"M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversation","date":"2022-06-05","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/emotionflow-capture-the-dialogue-level","title":"EmotionFlow: Capture the Dialogue Level Emotion Transitions","date":"2022-05-07","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/emocaps-emotion-capsule-based-model-for","title":"EmoCaps: Emotion Capsule based Model for Conversational Emotion Recognition","date":"2022-03-25","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/mm-dfn-multimodal-dynamic-fusion-network-for","title":"MM-DFN: Multimodal Dynamic Fusion Network for Emotion Recognition in Conversations","date":"2022-03-04","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":1,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/s-page-a-speaker-and-position-aware-graph","title":"S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation","date":"2021-12-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/contrast-and-generation-make-bart-a-good","title":"Contrast and Generation Make BART a Good Dialogue Emotion Recognizer","date":"2021-12-21","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/past-present-and-future-conversational","title":"Past, Present, and Future: Conversational Emotion Recognition through Structural Modeling of Psychological Knowledge","date":"2021-11-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/knowledge-interactive-network-with-sentiment","title":"Knowledge-Interactive Network with Sentiment Polarity Intensity-Aware Multi-Task Learning for Emotion Recognition in Conversations","date":"2021-11-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/a-discourse-aware-graph-neural-network-for","title":"A Discourse-Aware Graph Neural Network for Emotion Recognition in Multi-Party Conversation","date":"2021-11-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/graph-based-network-with-contextualized","title":"Graph Based Network with Contextualized Representations of Turns in Dialogue","date":"2021-09-09","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":10,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/emoberta-speaker-aware-emotion-recognition-in","title":"EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa","date":"2021-08-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/compm-context-modeling-with-speaker-s-pre","title":"CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in Conversation","date":"2021-08-26","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dialoguecrn-contextual-reasoning-networks-for","title":"DialogueCRN: Contextual Reasoning Networks for Emotion Recognition in Conversations","date":"2021-06-03","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/topic-driven-and-knowledge-aware-transformer","title":"Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection","date":"2021-06-02","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/directed-acyclic-graph-network-for","title":"Directed Acyclic Graph Network for Conversational Emotion Recognition","date":"2021-05-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-hierarchical-transformer-with-speaker","title":"A Hierarchical Transformer with Speaker Modeling for Emotion Recognition in Conversation","date":"2020-12-29","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/dialogxl-all-in-one-xlnet-for-multi-party","title":"DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition","date":"2020-12-16","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/summarize-before-aggregate-a-global-to-local","title":"Summarize before Aggregate: A Global-to-local Heterogeneous Graph Inference Network for Conversational Emotion Recognition","date":"2020-12-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/hitrans-a-transformer-based-context-and","title":"HiTrans: A Transformer-Based Context- and Speaker-Sensitive Model for Emotion Detection in Conversations","date":"2020-12-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/an-iterative-emotion-interaction-network-for","title":"An Iterative Emotion Interaction Network for Emotion Recognition in Conversations","date":"2020-12-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/relation-aware-graph-attention-networks-with","title":"Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations","date":"2020-11-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/cosmic-commonsense-knowledge-for-emotion","title":"COSMIC: COmmonSense knowledge for eMotion Identification in Conversations","date":"2020-10-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hierarchical-pre-training-for-sequence","title":"Hierarchical Pre-training for Sequence Labelling in Spoken Dialog","date":"2020-09-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/contextualized-emotion-recognition-in","title":"Contextualized Emotion Recognition in Conversation as Sequence Tagging","date":"2020-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/bieru-bidirectional-emotional-recurrent-unit","title":"BiERU: Bidirectional Emotional Recurrent Unit for Conversational Sentiment Analysis","date":"2020-05-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-task-learning-network-for-emotion","title":"Multi-Task Learning with Auxiliary Speaker Identification for Conversational Emotion Recognition","date":"2020-03-03","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/knowledge-enriched-transformer-for-emotion","title":"Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations","date":"2019-09-24","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/dialoguegcn-a-graph-convolutional-neural","title":"DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation","date":"2019-08-30","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":4,"samples_ran":0,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/modeling-both-context-and-speaker-sensitive","title":"Modeling both context- and speaker-sensitive dependence for emotion detection in multi-speaker conversations","date":"2019-07-01","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/dialoguernn-an-attentive-rnn-for-emotion","title":"DialogueRNN: An Attentive RNN for Emotion Detection in Conversations","date":"2018-11-01","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/context-dependent-sentiment-analysis-in-user","title":"Context-Dependent Sentiment Analysis in User-Generated Videos","date":"2017-07-01","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":8,"samples_harvested":44,"samples_ran":25,"samples_unverified":19,"pointer_only_for_licence":13,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}