{"url":"/sota/emotion-recognition-in-conversation-on-3","task":{"name":"Emotion Recognition in Conversation","url":"/task/emotion-recognition-in-conversation","note":null},"dataset":{"name":"DailyDialog","url":"/dataset/dailydialog"},"category":"Computer Vision","categories":["Audio","Computer Vision","Miscellaneous","Natural Language Processing","Speech"],"category_note":null,"description":"Given the transcript of a conversation along with speaker information of each constituent utterance, the ERC task aims to identify the emotion of each utterance from several pre-defined emotions. Formally, given the input sequence of N number of utterances [(u1, p1), (u2, p2), . . . , (uN , pN )], where each utterance ui = [ui,1, ui,2, . . . , ui,T ] consists of T words ui,j and spoken by party pi, the task is to predict the emotion label ei of each utterance ui.\r\n.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Micro-F1","Macro F1","Weighted F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Micro-F1":"higher","Macro F1":"higher","Weighted F1":"higher"}},"counts":{"rows":22,"rows_with_code":15,"rows_with_paper_page":22,"rows_dated":19,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"S+PAGE","metrics":{"Micro-F1":"64.07"},"uses_additional_data":false,"paper_date":"2021-12-23","paper":"/paper/s-page-a-speaker-and-position-aware-graph","paper_url":"https://arxiv.org/abs/2112.12389v1","paper_title":"S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"CESTa","metrics":{"Micro-F1":"63.12"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/contextualized-emotion-recognition-in","paper_url":"https://aclanthology.org/2020.sigdial-1.23","paper_title":"Contextualized Emotion Recognition in Conversation as Sequence Tagging","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"TUCORE-GCN_RoBERTa","metrics":{"Micro-F1":"61.91"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/graph-based-network-with-contextualized","paper_url":"https://arxiv.org/abs/2109.04008v1","paper_title":"Graph Based Network with Contextualized Representations of Turns in Dialogue","code":"https://github.com/blacknoodle/tucore-gcn","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"EmoOne-RoBERTa","metrics":{"Macro F1":"55.84","Micro-F1":"61.67"},"uses_additional_data":false,"paper_date":"2022-06-15","paper":"/paper/the-emotion-is-not-one-hot-encoding-learning","paper_url":"https://arxiv.org/abs/2206.07359v2","paper_title":"The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation","code":"https://github.com/rungjoo/Emotion_not_One","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"CoMPM","metrics":{"Macro F1":"53.15","Micro-F1":"60.34"},"uses_additional_data":false,"paper_date":"2021-08-26","paper":"/paper/compm-context-modeling-with-speaker-s-pre","paper_url":"https://arxiv.org/abs/2108.11626v3","paper_title":"CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in Conversation","code":"https://github.com/rungjoo/compm","n_code_links":1,"syntology":null},{"rank_in_archive_order":6,"model":"Pretrained Hierarchical Transformer","metrics":{"Micro-F1":"60.14"},"uses_additional_data":false,"paper_date":"2020-09-23","paper":"/paper/hierarchical-pre-training-for-sequence","paper_url":"https://arxiv.org/abs/2009.11152v3","paper_title":"Hierarchical Pre-training for Sequence Labelling in Spoken Dialog","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"EmotionIC","metrics":{"Macro F1":"54.19","Micro-F1":"60.13"},"uses_additional_data":false,"paper_date":"2023-03-20","paper":"/paper/emotionic-emotional-inertia-and-contagion","paper_url":"https://arxiv.org/abs/2303.11117v5","paper_title":"EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation","code":"https://github.com/lijfrank-open/EmotionIC","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"TODKAT+HCL","metrics":{"Micro-F1":"59.76"},"uses_additional_data":false,"paper_date":"2021-12-22","paper":"/paper/hybrid-curriculum-learning-for-emotion","paper_url":"https://arxiv.org/abs/2112.11718v2","paper_title":"Hybrid Curriculum Learning for Emotion Recognition in Conversation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":9,"model":"SKAIG-ERC","metrics":{"Macro F1":"51.95","Micro-F1":"59.75"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/past-present-and-future-conversational","paper_url":"https://aclanthology.org/2021.findings-emnlp.104","paper_title":"Past, Present, and Future: Conversational Emotion Recognition through Structural Modeling of Psychological Knowledge","code":"https://github.com/leqsnan/skaig-erc","n_code_links":1,"syntology":null},{"rank_in_archive_order":10,"model":"DAG-ERC","metrics":{"Micro-F1":"59.33"},"uses_additional_data":false,"paper_date":"2021-05-27","paper":"/paper/directed-acyclic-graph-network-for","paper_url":"https://arxiv.org/abs/2105.12907v2","paper_title":"Directed Acyclic Graph Network for Conversational Emotion Recognition","code":"https://github.com/shenwzh3/DAG-ERC","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"AccumWR","metrics":{"Micro-F1":"59.22"},"uses_additional_data":false,"paper_date":"2023-11-06","paper":"/paper/accumulating-word-representations-in-multi","paper_url":"https://ieeexplore.ieee.org/document/10299463","paper_title":"Accumulating Word Representations in Multi-level Context Integration for ERC Task","code":"https://github.com/yingjie7/per_erc","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"COSMIC","metrics":{"Macro F1":"51.05","Micro-F1":"58.48"},"uses_additional_data":false,"paper_date":"2020-10-06","paper":"/paper/cosmic-commonsense-knowledge-for-emotion","paper_url":"https://arxiv.org/abs/2010.02795v1","paper_title":"COSMIC: COmmonSense knowledge for eMotion Identification in Conversations","code":"https://github.com/declare-lab/conv-emotion","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"TODKAT","metrics":{"Micro-F1":"58.47","Weighted F1":"52.56"},"uses_additional_data":false,"paper_date":"2021-06-02","paper":"/paper/topic-driven-and-knowledge-aware-transformer","paper_url":"https://arxiv.org/abs/2106.01071v1","paper_title":"Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":14,"model":"TUCORE-GCN_BERT","metrics":{"Micro-F1":"58.34"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/graph-based-network-with-contextualized","paper_url":"https://arxiv.org/abs/2109.04008v1","paper_title":"Graph Based Network with Contextualized Representations of Turns in Dialogue","code":"https://github.com/blacknoodle/tucore-gcn","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":7,"n_samples":17,"n_pointer_only_licence":0}},{"rank_in_archive_order":15,"model":"KI-Net","metrics":{"Micro-F1":"57.30"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/knowledge-interactive-network-with-sentiment","paper_url":"https://aclanthology.org/2021.findings-emnlp.245","paper_title":"Knowledge-Interactive Network with Sentiment Polarity Intensity-Aware Multi-Task Learning for Emotion Recognition in Conversations","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"DialogXL","metrics":{"Micro-F1":"54.93"},"uses_additional_data":false,"paper_date":"2020-12-16","paper":"/paper/dialogxl-all-in-one-xlnet-for-multi-party","paper_url":"https://arxiv.org/abs/2012.08695v1","paper_title":"DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition","code":"https://github.com/shenwzh3/DialogXL","n_code_links":4,"syntology":null},{"rank_in_archive_order":17,"model":"CoG-BART","metrics":{"Micro-F1":"54.71","Weighted F1":"54.71"},"uses_additional_data":false,"paper_date":"2021-12-21","paper":"/paper/contrast-and-generation-make-bart-a-good","paper_url":"https://arxiv.org/abs/2112.11202v2","paper_title":"Contrast and Generation Make BART a Good Dialogue Emotion Recognizer","code":"https://github.com/whatissimondoing/cog-bart","n_code_links":1,"syntology":null},{"rank_in_archive_order":18,"model":"RGAT-ERC","metrics":{"Micro-F1":"54.31"},"uses_additional_data":false,"paper_date":null,"paper":"/paper/relation-aware-graph-attention-networks-with","paper_url":"https://aclanthology.org/2020.emnlp-main.597","paper_title":"Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations","code":"https://github.com/KomorebiLHX/Emotion-Recognition-in-Conversations","n_code_links":1,"syntology":null},{"rank_in_archive_order":19,"model":"KET","metrics":{"Micro-F1":"53.37"},"uses_additional_data":false,"paper_date":"2019-09-24","paper":"/paper/knowledge-enriched-transformer-for-emotion","paper_url":"https://arxiv.org/abs/1909.10681v2","paper_title":"Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations","code":"https://github.com/zhongpeixiang/KET","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":20,"model":"VHRED","metrics":{"Micro-F1":"48.4"},"uses_additional_data":false,"paper_date":"2019-10-11","paper":"/paper/emotion-recognition-in-conversations-with","paper_url":"https://arxiv.org/abs/1910.04980v3","paper_title":"Conversational Transfer Learning for Emotion Recognition","code":"https://github.com/SenticNet/conv-emotion","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"CD-ERC+FFP","metrics":{"Macro F1":"51.89"},"uses_additional_data":false,"paper_date":"2023-09-08","paper":"/paper/fuzzy-fingerprinting-transformer-language","paper_url":"https://arxiv.org/abs/2309.04292v1","paper_title":"Fuzzy Fingerprinting Transformer Language-Models for Emotion Recognition in Conversations","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"CD-ERC","metrics":{"Macro F1":"51.23"},"uses_additional_data":false,"paper_date":"2023-04-17","paper":"/paper/context-dependent-embedding-utterance","paper_url":"https://arxiv.org/abs/2304.08216v2","paper_title":"Context-Dependent Embedding Utterance Representations for Emotion Recognition in Conversations","code":"https://github.com/patricia-pereira/cd-erc","n_code_links":1,"syntology":null}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":5,"rows_with_any_sample_ran":4,"distinct_papers_with_graph_line":4,"distinct_papers_with_any_sample_ran":3,"samples_over_distinct_papers":{"n_ran":16,"n_unverified":10,"n_samples":26,"n_pointer_only_licence":3,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":26,"n_unverified":17,"n_samples":43,"n_pointer_only_licence":3,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}