{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:59:49Z","timestamp":1776931189718,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000},"content-version":"vor","delay-in-days":365,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2211550"],"award-info":[{"award-number":["IIS-2211550"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3716553.3750822","type":"proceedings-article","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:13:16Z","timestamp":1760188396000},"page":"721-725","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Modeling Social Dynamics from Multimodal Cues in Natural Conversations"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6387-5686","authenticated-orcid":false,"given":"Kevin","family":"Hyekang Joo","sequence":"first","affiliation":[{"name":"Thomas Lord Department of Computer Science, University of Southern California, Los Angeles, California, USA and Institute for Creative Technologies, University of Southern California, Los Angeles, California, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Oya Celiktutan Efstratios Skordos and Hatice Gunes. 2017. Multimodal human-human-robot interactions (mhhri) dataset for studying personality and engagement. IEEE Transactions on Affective Computing 10 4 (2017) 484\u2013497.","DOI":"10.1109\/TAFFC.2017.2737019"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00802"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Jared\u00a0R Curhan and Alex Pentland. 2007. Thin slices of negotiation: predicting outcomes from conversational dynamics within the first 5 minutes. Journal of Applied Psychology 92 3 (2007) 802.","DOI":"10.1037\/0021-9010.92.3.802"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"M.\u00a0Ali\u00a0Akber Dewan Mahbub Murshed and Fuhua Lin. 2019. Engagement detection in online learning: a review. Smart Learning Environments 6 1 (Jan. 2019) 1. 10.1186\/s40561-018-0080-z","DOI":"10.1186\/s40561-018-0080-z"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Paul Ekman and Wallace\u00a0V Friesen. 1978. Facial action coding system. Environmental Psychology & Nonverbal Behavior (1978).","DOI":"10.1037\/t27734-000"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"Jessie Hoegen David DeVault and Jonathan Gratch. 2022. Exploring the function of expressions in negotiation: The DyNego-WOZ corpus. IEEE Transactions on Affective Computing 14 4 (2022) 3376\u20133387.","DOI":"10.1109\/TAFFC.2022.3223030"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Adam\u00a0O Horvath and Leslie\u00a0S Greenberg. 1989. Development and validation of the Working Alliance Inventory. Journal of counseling psychology 36 2 (1989) 223.","DOI":"10.1037\/0022-0167.36.2.223"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Wei-Ning Hsu Benjamin Bolte Yao-Hung\u00a0Hubert Tsai Kushal Lakhotia Ruslan Salakhutdinov and Abdelrahman Mohamed. 2021. Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Transactions on Audio Speech and Language Processing 29 (2021) 3451\u20133460.","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"Paul H\u00f6mke Judith Holler and Stephen\u00a0C. Levinson. 2018. Eye blinks are perceived as communicative signals in human face-to-face interaction. PLOS ONE 13 12 (12 2018) 1\u201313. 10.1371\/journal.pone.0208030","DOI":"10.1371\/journal.pone.0208030"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3716553.3750818"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2018.8615851"},{"key":"e_1_3_3_1_13_2","unstructured":"Sangmin Lee Minzhi Li Bolin Lai Wenqi Jia Fiona Ryan Xu Cao Ozgur Kara Bikram Boote Weiyan Shi Diyi Yang et\u00a0al. 2024. Towards social AI: A survey on understanding social interactions. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.15316 (2024)."},{"key":"e_1_3_3_1_14_2","unstructured":"Yinhan Liu Myle Ott Naman Goyal Jingfei Du Mandar Joshi Danqi Chen Omer Levy Mike Lewis Luke Zettlemoyer and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1907.11692 (2019)."},{"key":"e_1_3_3_1_15_2","series-title":"(ICMI Companion \u201925)","volume-title":"Companion Proceedings of the 27th International Conference on Multimodal Interaction","author":"Ma* Cheng\u00a0Charles","year":"2025","unstructured":"Cheng\u00a0Charles Ma*, Kevin\u00a0Hyekang Joo*, Alexandria\u00a0K. Vail*, Sunreeta Bhattacharya, \u00c1lvaro Fern\u00e1ndez\u00a0Garc\u00eda, Kailana Baker-Matsuoka, Sheryl Mathew, Lori\u00a0L. Holt, and Fernando\u00a0De la Torre. 2025. Multimodal Fusion with LLMs for Engagement Prediction in Natural Conversation. In Companion Proceedings of the 27th International Conference on Multimodal Interaction (Canberra, Australia) (ICMI Companion \u201925). Association for Computing Machinery, New York, NY, USA. Best Workshop Paper Award."},{"key":"e_1_3_3_1_16_2","first-page":"139","volume-title":"Handbook of Personality: Theory and Research, 2nd Ed","author":"McCrae Robert\u00a0R.","year":"1999","unstructured":"Robert\u00a0R. McCrae and Paul\u00a0T. Costa\u00a0Jr.1999. A Five-Factor Theory of Personality. In Handbook of Personality: Theory and Research, 2nd Ed. Guilford Press, New York, NY, US, 139\u2013153."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","unstructured":"Peter Muntigl Naomi Knight and Ashley Watkins. 2012. Working to keep aligned in psychotherapy: Using nods as a dialogic resource to display affiliation. Language and Dialogue 2 1 (2012) 9\u201327. 10.1075\/ld.2.1.01mun","DOI":"10.1075\/ld.2.1.01mun"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610977.3634929"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Takayuki Osugi and Jun\u00a0I. Kawahara. 2018. Effects of Head Nodding and Shaking Motions on Perceptions of Likeability and Approachability. Perception 47 1 (2018) 16\u201329. 10.1177\/0301006617733209 arXiv:10.1177\/0301006617733209 PMID: 28945151.","DOI":"10.1177\/0301006617733209"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Arthur Pellet-Rostaing Roxane Bertrand Auriane Boudin St\u00e9phane Rauzy and Philippe Blache. 2023. A multimodal approach for modeling engagement in conversation. Frontiers in Computer Science 5 (2023) 1062342.","DOI":"10.3389\/fcomp.2023.1062342"},{"key":"e_1_3_3_1_21_2","volume-title":"Beyond Red vs. Blue: The Political Typology","author":"Center Pew Research","year":"2021","unstructured":"Pew Research Center. 2021. Beyond Red vs. Blue: The Political Typology. Technical Report. Pew Research Center, Washington, DC, USA."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.5555\/3618408.3619590"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553805"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3678957.3685752"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418832"},{"key":"e_1_3_3_1_26_2","volume-title":"13th IEEE International Conference on Automatic Face & Gesture Recognition","author":"Tadas Baltrusaitis","year":"2018","unstructured":"Baltrusaitis Tadas, Zadeh Amir, Lim\u00a0Yao Chong, and Louis-Morency Philippe. 2018. Openface 2.0: Facial behavior analysis toolkit. In 13th IEEE International Conference on Automatic Face & Gesture Recognition."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Adriana Tapus Maja Mataric and Brian Scassellati. 2009. Socially assistive robotics [Grand Challenges of Robotics]. IEEE Robotics & Automation Magazine 14 1 (2009) 35\u201342.","DOI":"10.1109\/MRA.2007.339605"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614105"}],"event":{"name":"ICMI '25: International Conference on Multimodal Interaction","location":"Canberra Australia","acronym":"ICMI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 27th International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3716553.3750822","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3716553.3750822","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T22:25:47Z","timestamp":1769466347000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716553.3750822"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":27,"alternative-id":["10.1145\/3716553.3750822","10.1145\/3716553"],"URL":"https:\/\/doi.org\/10.1145\/3716553.3750822","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"2025-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}