{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T03:36:29Z","timestamp":1782358589038,"version":"3.54.5"},"reference-count":155,"publisher":"Association for Computing Machinery (ACM)","issue":"7","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62072462"],"award-info":[{"award-number":["62072462"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Beijing Natural Science Foundation","award":["L233008"],"award-info":[{"award-number":["L233008"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2025,7,31]]},"abstract":"<jats:p>Deep learning has shown impressive performance in affective computing, but its black-box characteristic limits the model\u2019s interpretability, posing a challenge to further development and application. Compared with objective recognition tasks such as image recognition, emotion perception as a high-level cognition is more subjective, making it particularly important to enhance the interpretability of deep learning in affective computing. In recent years, some interpretability-related works have emerged, but there are few reviews on this topic yet. This article summarizes the explainable deep learning methods in affective computing from two aspects: first, the application of general explainable deep learning methods in affective computing from the perspectives of model-agnostic and model-specific is introduced; second, emotion-specific interpretability research that combines emotional psychology theories, physiological studies, and human cognition, covering task design, model design, and result analysis methods, is systematically reviewed. There are new explainable deep learning methods for multimodal and large language models in the context of emotion. Finally, we discuss five specific challenges and propose corresponding future directions to provide insights and references for subsequent research on affective computing interpretability.<\/jats:p>","DOI":"10.1145\/3723005","type":"journal-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T12:04:03Z","timestamp":1741781043000},"page":"1-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["Exploring Interpretability in Deep Learning for Affective Computing: A Comprehensive Review"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7672-6778","authenticated-orcid":false,"given":"Xinjie","family":"Zhang","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9794-9578","authenticated-orcid":false,"given":"Tenggan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1035-407X","authenticated-orcid":false,"given":"Lei","family":"Sun","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1497-8865","authenticated-orcid":false,"given":"Jinming","family":"Zhao","sequence":"additional","affiliation":[{"name":"Independent Researcher, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6486-6020","authenticated-orcid":false,"given":"Qin","family":"Jin","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,19]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Samira Abnar and Willem Zuidema. 2020. Quantifying attention flow in transformers. arXiv:2005.0092. Retrieved from https:\/\/arxiv.org\/abs\/2005.00928","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00642"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT58233.2024.10540745"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3307716"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3035535"},{"key":"e_1_3_1_7_2","unstructured":"Anna Aljanaki and Mohammad Soleymani. 2018. A data-driven approach to mid-level perceptual musical feature modeling. arXiv:1806.04903. Retrieved from https:\/\/arxiv.org\/abs\/1806.04903"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICAECT54875.2022.9807868"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892315"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.25"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993165"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10582016"},{"key":"e_1_3_1_14_2","volume-title":"Sentiment Analysis and Opinion Mining (Synthesis Lectures on Human Language Technologies)","author":"Liu Bing","year":"2012","unstructured":"Liu Bing. 2012. Sentiment Analysis and Opinion Mining (Synthesis Lectures on Human Language Technologies). University of Illinois, Chicago, IL."},{"issue":"1","key":"e_1_3_1_15_2","first-page":"4","article-title":"Qlime-a quadratic local interpretable model-agnostic explanation approach","volume":"3","author":"Bramhall Steven","year":"2020","unstructured":"Steven Bramhall, Hayley Horn, Michael Tieu, and Nibhrat Lohia. 2020. Qlime-a quadratic local interpretable model-agnostic explanation approach. SMU Data Science Review 3, 1 (2020), 4.","journal-title":"SMU Data Science Review"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.29"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"e_1_3_1_20_2","article-title":"This looks like that: Deep learning for interpretable image recognition","author":"Chen Chaofan","year":"2019","unstructured":"Chaofan Chen, Oscar Li, Chaofan Tao, Alina Jade Barnet, Jonathan Su, and Cynthia Rudin. 2019. This looks like that: Deep learning for interpretable image recognition. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, 8930\u20138941.","journal-title":"In Proceedings of the 33rd International Conference on Neural Information Processing Systems, 8930\u20138941."},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.112"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2024.3365174"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/1873781.1873802"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-81462-5_9"},{"key":"e_1_3_1_25_2","unstructured":"Shreyan Chowdhury Andreu Vall Verena Haunschmid and Gerhard Widmer. 2019. Towards explainable music emotion recognition: The route via mid-level features. arXiv:1907.03572. Retrieved from https:\/\/arxiv.org\/abs\/1907.03572"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.40"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3270027"},{"key":"e_1_3_1_28_2","unstructured":"Sneha Das Nicole Nadine L\u00f8nfeldt Anne Katrine Pagsberg and Line H. Clemmensen. 2021. Towards interpretable and transferable speech emotion recognition: Latent representation based analysis of features methods and corpora. arXiv:2105.02055. Retrieved from https:\/\/arxiv.org\/abs\/2105.02055"},{"key":"e_1_3_1_29_2","first-page":"4794","volume-title":"International Conference on Machine Learning","author":"Dasgupta Sanjoy","unstructured":"Sanjoy Dasgupta, Nave Frost, and Michal Moshkovitz. 2022. Framework for evaluating faithfulness of local explanations. In International Conference on Machine Learning. PMLR, 4794\u20134815."},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/IST50367.2021.9651357"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.408"},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107177"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-2009"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1080\/1351847X.2020.1742758"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114784"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.101"},{"key":"e_1_3_1_37_2","first-page":"105","article-title":"Encountering emotion in healthcare","author":"Fitzgerald Jennifer","year":"2016","unstructured":"Jennifer Fitzgerald. 2016. Encountering emotion in healthcare. Psychosocial Dimensions of Medicine, 105\u2013117.","journal-title":"Psychosocial Dimensions of Medicine"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","unstructured":"Hortense Fong Vineet Kumar and K. Sudhir. 2023. A theory-based interpretable deep learning architecture for music emotion. DOI: 10.2139\/ssrn.4025386","DOI":"10.2139\/ssrn.4025386"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.08.009"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3048693"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG52635.2021.9667052"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-18117-2_12"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.224"},{"key":"e_1_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"e_1_3_1_46_2","unstructured":"Yash Goyal Amir Feder Uri Shalit and Been Kim. 2019. Explaining classifiers with causal concept effect (CaCE). arXiv:1907.07165. Retrieved from https:\/\/arxiv.org\/abs\/1907.07165"},{"key":"e_1_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59830-3_32"},{"key":"e_1_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-2993-6_8"},{"key":"e_1_3_1_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412134"},{"key":"e_1_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243792"},{"key":"e_1_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.3390\/s21155015"},{"key":"e_1_3_1_52_2","unstructured":"Verena Haunschmid Shreyan Chowdhury and Gerhard Widmer. 2019. Two-level explanations in music emotion recognition. arXiv:1905.11760. Retrieved from https:\/\/arxiv.org\/abs\/1905.11760"},{"key":"e_1_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3326593"},{"key":"e_1_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.3043603"},{"key":"e_1_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014073"},{"key":"e_1_3_1_56_2","unstructured":"Zhaopei Huang Jinming Zhao and Qin Jin. 2024. ECR-Chain: Advancing generative language models to better emotion-cause reasoners through reasoning chains. arXiv:2405.10860. Retrieved from https:\/\/arxiv.org\/abs\/2405.10860"},{"key":"e_1_3_1_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511941"},{"key":"e_1_3_1_58_2","first-page":"493","volume-title":"European Conference on Computer Vision","author":"Jia Guoli","year":"2022","unstructured":"Guoli Jia and Jufeng Yang. 2022. S2-VER: Semi-supervised visual emotion recognition. In European Conference on Computer Vision. Springer, 493\u2013509."},{"key":"e_1_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103501"},{"key":"e_1_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1111\/exsy.13403"},{"key":"e_1_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2780838"},{"key":"e_1_3_1_62_2","first-page":"2668","volume-title":"International Conference on Machine Learning. PMLR","author":"Kim Been","year":"2018","unstructured":"Been Kim, Martin Wattenberg, Justin Gilmer, Carrie Cai, James Wexler, Fernanda Viegas, Rory Sayres. 2018. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (TCAV). In International Conference on Machine Learning. PMLR, 2668\u20132677."},{"key":"e_1_3_1_63_2","doi-asserted-by":"publisher","DOI":"10.1109\/BIGCOMP.2019.8679370"},{"key":"e_1_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_14"},{"key":"e_1_3_1_65_2","first-page":"1885","volume-title":"International Conference on Machine Learning","author":"Koh Pang Wei","year":"2017","unstructured":"Pang Wei Koh and Percy Liang. 2017. Understanding black-box predictions via influence functions. In International Conference on Machine Learning. PMLR, 1885\u20131894."},{"key":"e_1_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00408"},{"key":"e_1_3_1_67_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1718"},{"key":"e_1_3_1_68_2","unstructured":"Puneet Kumar Sarthak Malik and Balasubramanian Raman. 2022. Hybrid fusion based interpretable multimodal emotion recognition with insufficient labelled data. arXiv:2208.11450. Retrieved from https:\/\/arxiv.org\/abs\/2208.11450"},{"key":"e_1_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-023-16443-1"},{"key":"e_1_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.03.017"},{"key":"e_1_3_1_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01024"},{"key":"e_1_3_1_72_2","first-page":"45","volume-title":"Workshop on Computational Approaches to Analysis and Generation of Emotion in Text (NAACL HLT \u201910)","author":"Lee Sophia Yat Mei","year":"2010","unstructured":"Sophia Yat Mei Lee, Ying Chen, and Chu-Ren Huang. 2010. A text-driven rule-based system for emotion cause detection. In Workshop on Computational Approaches to Analysis and Generation of Emotion in Text (NAACL HLT \u201910), 45\u201353."},{"key":"e_1_3_1_73_2","unstructured":"Yoon Kyung Lee Inju Lee Minjung Shin Seoyeon Bae and Sowon Hahn. 2023. Chain of empathy: Enhancing empathetic response of large language models based on psychotherapy models. arXiv:2311.04915. Retrieved from https:\/\/arxiv.org\/abs\/2311.04915"},{"key":"e_1_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3689646"},{"key":"e_1_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3049630"},{"key":"e_1_3_1_76_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21347"},{"key":"e_1_3_1_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"e_1_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"e_1_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581918"},{"key":"e_1_3_1_80_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-022-01756-8"},{"key":"e_1_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2023.114121"},{"key":"e_1_3_1_82_2","first-page":"986","volume-title":"8th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"Li Yanran","year":"2017","unstructured":"Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. DailyDialog: A manually labelled multi-turn dialogue dataset. In 8th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 986\u2013995."},{"key":"e_1_3_1_83_2","unstructured":"Zaijing Li Gongwei Chen Rui Shao Dongmei Jiang and Liqiang Nie. 2024. Enhancing the emotional generation capability of large language models via emotional chain-of-thought. arXiv:2401.06836. Retrieved from https:\/\/arxiv.org\/abs\/2401.06836"},{"key":"e_1_3_1_84_2","unstructured":"Zheng Lian Haiyang Sun Licai Sun Jiangyan Yi Bin Liu and Jianhua Tao. 2024. AffectGPT: Dataset and framework for explainable multimodal emotion recognition. arXiv:2407.07653. Retrieved from https:\/\/arxiv.org\/abs\/2407.07653"},{"key":"e_1_3_1_85_2","unstructured":"Zheng Lian Licai Sun Mingyu Xu Haiyang Sun Ke Xu Zhuofan Wen Shun Chen Bin Liu and Jianhua Tao. 2023. Explainable multimodal emotion reasoning. arXiv:2306.15401. Retrieved from https:\/\/arxiv.org\/abs\/2306.15401"},{"key":"e_1_3_1_86_2","volume-title":"11th International Conference on Learning Representations","author":"Liang Paul Pu","year":"2022","unstructured":"Paul Pu Liang, Yiwei Lyu, Gunjan Chhablani, Nihal Jain, Zihao Deng, Xingbo Wang, Louis-Philippe Morency, and Ruslan Salakhutdinov. 2022. MultiViz: Towards visualizing and understanding multimodal models. In 11th International Conference on Learning Representations."},{"key":"e_1_3_1_87_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.269"},{"key":"e_1_3_1_88_2","unstructured":"Yiren Liu and Halil Kilicoglu. 2023. Commonsense-aware prompting for controllable empathetic dialogue generation. arXiv:2302.01441. Retrieved from https:\/\/arxiv.org\/abs\/2302.01441"},{"key":"e_1_3_1_89_2","first-page":"13807","volume-title":"International Conference on Machine Learning","author":"Liu Yibing","year":"2022","unstructured":"Yibing Liu, Haoliang Li, Yangyang Guo, Chenqi Kong, Jing Li, and Shiqi Wang. 2022. Rethinking attention-model explainability through faithfulness violation test. In International Conference on Machine Learning. PMLR, 13807\u201313824."},{"issue":"5","key":"e_1_3_1_90_2","doi-asserted-by":"crossref","first-page":"e0196391","DOI":"10.1371\/journal.pone.0196391","article-title":"The Ryerson audio-visual database of emotional speech and song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English","volume":"13","year":"2018","unstructured":"Steven R. and Livingstone, Frank A. Russo. 2018. The Ryerson audio-visual database of emotional speech and song (RAVDESS): A dynamic, multimodal set of facial and vocal expressions in North American English. Plos One 13, 5 (2018), e0196391.","journal-title":"Plos One"},{"key":"e_1_3_1_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"e_1_3_1_92_2","first-page":"4768","article-title":"A unified approach to interpreting model predictions","author":"Lundberg Scott M.","year":"2017","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems, 4768\u20134777.","journal-title":"In Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"e_1_3_1_93_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1056"},{"key":"e_1_3_1_94_2","unstructured":"Michael Lyons Miyuki Kamachi and Jiro Gyoba. 1998. The Japanese female facial expression (JAFFE) dataset. Retrieved from https:\/\/zenodo.org\/records\/3451524"},{"key":"e_1_3_1_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490035.3490271"},{"issue":"4","key":"e_1_3_1_96_2","first-page":"153","article-title":"Behavioral finance: New research trends, socionomics and investor emotions","volume":"21","author":"Mitroi Adrian","year":"2014","unstructured":"Adrian Mitroi and Alexandru Oproiu. 2014. Behavioral finance: New research trends, socionomics and investor emotions. Theoretical and Applied Economics 21, 4 (2014), 153\u2013166.","journal-title":"Theoretical and Applied Economics"},{"key":"e_1_3_1_97_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2740923"},{"key":"e_1_3_1_98_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-024-05536-5"},{"key":"e_1_3_1_99_2","unstructured":"Daniel Omeiza Skyler Speakman Celia Cintas and Komminist Weldermariam. 2019. Smooth grad-cam++: An enhanced inference level visualization technique for deep convolutional neural network models. arXiv:1908.01224. Retrieved from https:\/\/arxiv.org\/abs\/1908.01224"},{"key":"e_1_3_1_100_2","unstructured":"OpenAI. 2022. Introducing ChatGPT. Retrieved from https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_3_1_101_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3304015"},{"key":"e_1_3_1_102_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6383"},{"key":"e_1_3_1_103_2","article-title":"Model agnostic supervised local explanations","author":"Plumb Gregory","year":"2018","unstructured":"Gregory Plumb, Denali Molitor, and Ameet S. Talwalkar. 2018. Model agnostic supervised local explanations. In Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2520\u20132529.","journal-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems"},{"key":"e_1_3_1_104_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S16-1002"},{"key":"e_1_3_1_105_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S15-2082"},{"key":"e_1_3_1_106_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/S14-2004"},{"key":"e_1_3_1_107_2","unstructured":"Soujanya Poria Devamanyu Hazarika Navonil Majumder Gautam Naik Erik Cambria and Rada Mihalcea. 2018. Meld: A multimodal multi-party dataset for emotion recognition in conversations. arXiv:1810.02508. Retrieved from https:\/\/arxiv.org\/abs\/1810.02508"},{"key":"e_1_3_1_108_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-021-09925-7"},{"key":"e_1_3_1_109_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-98358-1_25"},{"key":"e_1_3_1_110_2","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00034"},{"key":"e_1_3_1_111_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22208066"},{"key":"e_1_3_1_112_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_1_113_2","first-page":"153","volume-title":"In 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (WASSA\u201911)","author":"Russo Irene","year":"2011","unstructured":"Irene Russo, Tommaso Caselli, Francesco Rubino, Ester Boldrini, and Patricio Mart\u00ednez-Barco. 2011. EMOCause: An easy-adaptable approach to extract emotion cause contexts. In 2nd Workshop on Computational Approaches to Subjectivity and Sentiment Analysis (WASSA\u201911), 153\u2013160."},{"key":"e_1_3_1_114_2","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.66.2.310"},{"key":"e_1_3_1_115_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_1_116_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2008.08.005"},{"issue":"1","key":"e_1_3_1_117_2","first-page":"356","article-title":"Reliable crowdsourcing and deep locality-preserving learning for unconstrained facial expression recognition","volume":"28","author":"Shan Li","year":"2018","unstructured":"Li Shan and Weihong Deng. 2018. Reliable crowdsourcing and deep locality-preserving learning for unconstrained facial expression recognition. IEEE Transactions on Image Processing 28, 1 (2018), 356\u2013370.","journal-title":"IEEE Transactions on Image Processing"},{"key":"e_1_3_1_118_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413909"},{"key":"e_1_3_1_119_2","unstructured":"Sheng Shi Xinfeng Zhang and Wei Fan. 2020. A modified perturbed sampling method for local interpretable model-agnostic explanation. arXiv:2002.07434. Retrieved from https:\/\/arxiv.org\/abs\/2002.07434"},{"key":"e_1_3_1_120_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2865044"},{"key":"e_1_3_1_121_2","unstructured":"Mukund Sundararajan Ankur Taly and Qiqi Yan. 2017. Axiomatic attribution for deep networks. arXiv:1703.01365. Retrieved from https:\/\/arxiv.org\/abs\/1703.01365"},{"key":"e_1_3_1_122_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02024"},{"key":"e_1_3_1_123_2","doi-asserted-by":"publisher","DOI":"10.1007\/11573548_125"},{"key":"e_1_3_1_124_2","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv:2307.09288. Retrieved from https:\/\/arxiv.org\/abs\/2307.09288"},{"key":"e_1_3_1_125_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.143"},{"key":"e_1_3_1_126_2","unstructured":"Linh Vu Thu Tran Wern-Han Lim and Raphael Phan. 2024. Toward end-to-end interpretable convolutional neural networks for waveform signals. arXiv:2405.01815. Retrieved from https:\/\/arxiv.org\/abs\/2405.01815"},{"key":"e_1_3_1_127_2","doi-asserted-by":"publisher","DOI":"10.1609\/icwsm.v18i1.31412"},{"key":"e_1_3_1_128_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3226559"},{"key":"e_1_3_1_129_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489042"},{"key":"e_1_3_1_130_2","doi-asserted-by":"crossref","unstructured":"Hongru Wang Rui Wang Fei Mi Yang Deng Zezhong Wang Bin Liang Ruifeng Xu and Kam-Fai Wong. 2023. Cue-CoT: Chain-of-thought prompting for responding to in-depth dialogue questions with LLMs. arXiv:2305.11792. Retrieved from https:\/\/arxiv.org\/abs\/2305.11792","DOI":"10.18653\/v1\/2023.findings-emnlp.806"},{"key":"e_1_3_1_131_2","doi-asserted-by":"crossref","unstructured":"Jiawen Wang and Leah Kawka. 2024. GiMeFive: Towards interpretable facial emotion classification. arXiv:2402.15662. Retrieved from https:\/\/arxiv.org\/abs\/2402.15662","DOI":"10.21203\/rs.3.rs-3997302\/v1"},{"key":"e_1_3_1_132_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107547"},{"key":"e_1_3_1_133_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114794"},{"key":"e_1_3_1_134_2","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V. Le, and Denny Zhou. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems 35, 24824\u201324837.","journal-title":"Advances in Neural Information Processing Systems 35"},{"key":"e_1_3_1_135_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1096"},{"key":"e_1_3_1_136_2","unstructured":"Yuan Xia Jingbo Zhou Zhenhui Shi Jun Chen and Haifeng Huang. 2024. Improving retrieval augmented language model with self-reasoning. arXiv:2407.19813. Retrieved from https:\/\/arxiv.org\/abs\/2407.19813"},{"key":"e_1_3_1_137_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.108055"},{"key":"e_1_3_1_138_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01822"},{"key":"e_1_3_1_139_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00608"},{"key":"e_1_3_1_140_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01864"},{"key":"e_1_3_1_141_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.370"},{"key":"e_1_3_1_142_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1017"},{"key":"e_1_3_1_143_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3551609"},{"key":"e_1_3_1_144_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"e_1_3_1_145_2","unstructured":"Muhammad Rehman Zafar and Naimul Mefraz Khan. 2019. DLIME: A deterministic local interpretable model-agnostic explanations approach for computer-aided diagnosis systems. arXiv:1906.10263. Retrieved from https:\/\/arxiv.org\/abs\/1906.10263"},{"key":"e_1_3_1_146_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2963659"},{"issue":"1","key":"e_1_3_1_147_2","first-page":"927","article-title":"EmoCo: Visual analysis of emotion coherence in presentation videos","volume":"26","author":"Zeng Haipeng","year":"2019","unstructured":"Haipeng Zeng, Xingbo Wang, Aoyu Wu, Yong Wang, Quan Li, Alex Endert, and Huamin Qu. 2019. EmoCo: Visual analysis of emotion coherence in presentation videos. IEEE Transactions on Visualization and Computer Graphics 26, 1 (2019), 927\u2013937.","journal-title":"IEEE Transactions on Visualization and Computer Graphics"},{"key":"e_1_3_1_148_2","unstructured":"Tenggan Zhang Xinjie Zhang Jinming Zhao Li Zhou and Qin Jin. 2024. ESCoT: Towards interpretable emotional support dialogue systems. arXiv:2406.10960. Retrieved from https:\/\/arxiv.org\/abs\/2406.10960"},{"key":"e_1_3_1_149_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3230975"},{"key":"e_1_3_1_150_2","volume-title":"11th International Conference on Learning Representations","author":"Zhang Zhuosheng","year":"2022","unstructured":"Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2022. Automatic chain of thought prompting in large language models. In 11th International Conference on Learning Representations."},{"key":"e_1_3_1_151_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.861"},{"key":"e_1_3_1_152_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"e_1_3_1_153_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340555.3355713"},{"key":"e_1_3_1_154_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191181"},{"key":"e_1_3_1_155_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2828819"},{"key":"e_1_3_1_156_2","volume-title":"2022 ACM\/IEEE Workshop on Context-Awareness in Human-Robot Interaction Approaches and Challenges","author":"Zhu Hongbo","year":"2022","unstructured":"Hongbo Zhu, Chuang Yu, and Angelo Cangelosi. 2022. Explainable emotion recognition for trustworthy human-robot interaction. In 2022 ACM\/IEEE Workshop on Context-Awareness in Human-Robot Interaction Approaches and Challenges."}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3723005","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T21:42:38Z","timestamp":1772228558000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3723005"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,19]]},"references-count":155,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7,31]]}},"alternative-id":["10.1145\/3723005"],"URL":"https:\/\/doi.org\/10.1145\/3723005","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"value":"1551-6857","type":"print"},{"value":"1551-6865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,19]]},"assertion":[{"value":"2024-08-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}