{"url":"/sota/multimodal-sentiment-analysis-on-mosi","task":{"name":"Multimodal Sentiment Analysis","url":"/task/multimodal-sentiment-analysis","note":null},"dataset":{"name":"MOSI","url":"/dataset/multimodal-opinionlevel-sentiment-intensity"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"Multimodal sentiment analysis is the task of performing sentiment analysis with multiple data sources - e.g. a camera feed of someone's face and their recorded speech.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [ICON: Interactive Conversational Memory Network\r\nfor Multimodal Emotion Detection](https://www.aclweb.org/anthology/D18-1280.pdf) )</span>","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":["Accuracy","F1 score"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Accuracy":"higher","F1 score":"higher"}},"counts":{"rows":11,"rows_with_code":10,"rows_with_paper_page":11,"rows_dated":11,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MMML","metrics":{"Accuracy":"90.35","F1 score":"90.35"},"uses_additional_data":false,"paper_date":"2023-08-01","paper":"/paper/multi-modality-multi-loss-fusion-network","paper_url":"https://arxiv.org/abs/2308.00264v4","paper_title":"Multimodal Multi-loss Fusion Network for Sentiment Analysis","code":"https://github.com/zehuiwu/MMML","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"SPECTRA","metrics":{"Accuracy":"87.50"},"uses_additional_data":false,"paper_date":"2023-05-19","paper":"/paper/speech-text-dialog-pre-training-for-spoken","paper_url":"https://arxiv.org/abs/2305.11579v2","paper_title":"Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment","code":"https://github.com/alibabaresearch/damo-convai","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"UniMSE","metrics":{"Accuracy":"86.9","F1 score":"86.42"},"uses_additional_data":false,"paper_date":"2022-11-21","paper":"/paper/unimse-towards-unified-multimodal-sentiment","paper_url":"https://arxiv.org/abs/2211.11256v1","paper_title":"UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition","code":"https://github.com/lemei/unimse","n_code_links":1,"syntology":null},{"rank_in_archive_order":4,"model":"CM-BERT","metrics":{"Accuracy":"84.5%","F1 score":"84.5%"},"uses_additional_data":false,"paper_date":"2020-10-12","paper":"/paper/cross-modal-bert-for-text-audio-sentiment","paper_url":"https://dl.acm.org/doi/10.1145/3394171.3413690","paper_title":"Cross-Modal BERT for Text-Audio Sentiment Analysis","code":"https://github.com/thuiar/Cross-Modal-BERT","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"Proposed: B2 + B4 w/ multimodal fusion","metrics":{"Accuracy":"83.91%","F1 score":"81.17"},"uses_additional_data":false,"paper_date":"2020-02-21","paper":"/paper/gated-mechanism-for-attention-based","paper_url":"https://arxiv.org/abs/2003.01043v1","paper_title":"Gated Mechanism for Attention Based Multimodal Sentiment Analysis","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"MulT","metrics":{"Accuracy":"83","F1 score":"82.8"},"uses_additional_data":false,"paper_date":"2019-06-01","paper":"/paper/190600295","paper_url":"https://arxiv.org/abs/1906.00295v1","paper_title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","code":"https://github.com/yaohungt/Multimodal-Transformer","n_code_links":4,"syntology":{"n_ran":8,"n_unverified":9,"n_samples":17,"n_pointer_only_licence":10}},{"rank_in_archive_order":7,"model":"MMMU-BA","metrics":{"Accuracy":"82.31%"},"uses_additional_data":false,"paper_date":"2018-10-01","paper":"/paper/contextual-inter-modal-attention-for-multi","paper_url":"https://aclanthology.org/D18-1382","paper_title":"Contextual Inter-modal Attention for Multi-modal Sentiment Analysis","code":"https://github.com/soujanyaporia/contextual-multimodal-fusion","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"Multilogue-Net","metrics":{"Accuracy":"81.19"},"uses_additional_data":false,"paper_date":"2020-07-01","paper":"/paper/multilogue-net-a-context-aware-rnn-for-multi-2","paper_url":"https://aclanthology.org/2020.challengehml-1.3","paper_title":"Multilogue-Net: A Context-Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation","code":"https://github.com/amanshenoy/multilogue-net","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"bc-LSTM","metrics":{"Accuracy":"80.3%"},"uses_additional_data":false,"paper_date":"2017-07-01","paper":"/paper/context-dependent-sentiment-analysis-in-user","paper_url":"https://aclanthology.org/P17-1081","paper_title":"Context-Dependent Sentiment Analysis in User-Generated Videos","code":"https://github.com/soujanyaporia/multimodal-sentiment-analysis","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"MARN","metrics":{"Accuracy":"77.1%"},"uses_additional_data":false,"paper_date":"2018-02-03","paper":"/paper/multi-attention-recurrent-network-for-human","paper_url":"http://arxiv.org/abs/1802.00923v1","paper_title":"Multi-attention Recurrent Network for Human Communication Comprehension","code":"https://github.com/pliang279/MFN","n_code_links":2,"syntology":null},{"rank_in_archive_order":11,"model":"CHFusion","metrics":{"Accuracy":"76.5%"},"uses_additional_data":false,"paper_date":"2018-06-16","paper":"/paper/multimodal-sentiment-analysis-using","paper_url":"http://arxiv.org/abs/1806.06228v1","paper_title":"Multimodal Sentiment Analysis using Hierarchical Fusion with Context Modeling","code":"https://github.com/SenticNet/hfusion","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":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":8,"n_unverified":9,"n_samples":17,"n_pointer_only_licence":10,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":8,"n_unverified":9,"n_samples":17,"n_pointer_only_licence":10,"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"}}}