{"url":"/dataset/multimodal-opinionlevel-sentiment-intensity","name":"Multimodal Opinionlevel Sentiment Intensity","full_name":"MOSI","description_markdown":"Multimodal Opinionlevel Sentiment Intensity (MOSI) contains: (1) multimodal observations including transcribed speech and visual gestures as well as automatic audio and visual features, (2) opinion-level subjectivity segmentation, (3) sentiment intensity annotations with high coder agreement, and (4) alignment between words, visual and acoustic features.\r\n\r\nSource: [Zadeh et al](https://arxiv.org/pdf/1606.06259.pdf)\r\n\r\nImage source: [Zadeh et al](https://arxiv.org/pdf/1606.06259.pdf)","description_withheld":null,"homepage":"https://arxiv.org/pdf/1606.06259.pdf","introduced_date":"2016-06-20","introduced_date_note":null,"introduced_by":{"paper":"/paper/mosi-multimodal-corpus-of-sentiment-intensity","title":"MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos","first_author":"Amir Zadeh","url":null},"license":null,"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Multimodal Sentiment Analysis","url":"/task/multimodal-sentiment-analysis","datasets_with_task":"/datasets/task/multimodal-sentiment-analysis"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MOSI","Multimodal Opinionlevel Sentiment Intensity"],"data_loaders":[{"repo":"https://github.com/lobracost/MultimodalSDK_loader","url":"https://github.com/lobracost/MultimodalSDK_loader","frameworks":[]}],"num_papers_in_archive":69,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multimodal-sentiment-analysis-on-mosi","task":"Multimodal Sentiment Analysis","dataset_variant":"MOSI","rows":11,"metrics":["Accuracy","F1 score"],"first_row_in_archive_order":{"model":"MMML","paper":"/paper/multi-modality-multi-loss-fusion-network","metrics":{"Accuracy":"90.35","F1 score":"90.35"},"code_links":[{"title":"zehuiwu/MMML","url":"https://github.com/zehuiwu/MMML"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/multi-modality-multi-loss-fusion-network","title":"Multimodal Multi-loss Fusion Network for Sentiment Analysis","date":"2023-08-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/speech-text-dialog-pre-training-for-spoken","title":"Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment","date":"2023-05-19","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/cross-modal-bert-for-text-audio-sentiment","title":"Cross-Modal BERT for Text-Audio Sentiment Analysis","date":"2020-10-12","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multilogue-net-a-context-aware-rnn-for-multi-2","title":"Multilogue-Net: A Context-Aware RNN for Multi-modal Emotion Detection and Sentiment Analysis in Conversation","date":"2020-07-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/gated-mechanism-for-attention-based","title":"Gated Mechanism for Attention Based Multimodal Sentiment Analysis","date":"2020-02-21","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/190600295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","date":"2019-06-01","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":8,"samples_unverified":9,"pointer_only_for_licence":10,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/contextual-inter-modal-attention-for-multi","title":"Contextual Inter-modal Attention for Multi-modal Sentiment Analysis","date":"2018-10-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multimodal-sentiment-analysis-using","title":"Multimodal Sentiment Analysis using Hierarchical Fusion with Context Modeling","date":"2018-06-16","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/multi-attention-recurrent-network-for-human","title":"Multi-attention Recurrent Network for Human Communication Comprehension","date":"2018-02-03","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":1,"samples_harvested":17,"samples_ran":8,"samples_unverified":9,"pointer_only_for_licence":10,"papers_with_no_sample_that_ran":0,"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."}