{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T14:40:03Z","timestamp":1755873603320,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T00:00:00Z","timestamp":1695081600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,9,19]]},"DOI":"10.1145\/3570945.3607304","type":"proceedings-article","created":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T06:07:02Z","timestamp":1703225222000},"page":"1-4","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Study of Prediction of Listener's Comprehension Based on Multimodal Information"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7683-2879","authenticated-orcid":false,"given":"Shunichi","family":"Kinoshita","sequence":"first","affiliation":[{"name":"Nihon University, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4604-5396","authenticated-orcid":false,"given":"Toshiki","family":"Onishi","sequence":"additional","affiliation":[{"name":"Nihon University, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5653-3776","authenticated-orcid":false,"given":"Naoki","family":"Azuma","sequence":"additional","affiliation":[{"name":"Nihon University, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3849-1656","authenticated-orcid":false,"given":"Ryo","family":"Ishii","sequence":"additional","affiliation":[{"name":"NTT Corporation Kanagawa, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2133-016X","authenticated-orcid":false,"given":"Atsushi","family":"Fukayama","sequence":"additional","affiliation":[{"name":"NTT Corporation Kanagawa, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8267-871X","authenticated-orcid":false,"given":"Takao","family":"Nakamura","sequence":"additional","affiliation":[{"name":"NTT Corporation, Kanagawa, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4010-9487","authenticated-orcid":false,"given":"Akihiro","family":"Miyata","sequence":"additional","affiliation":[{"name":"Nihon University, Tokyo, Japan"}]}],"member":"320","published-online":{"date-parts":[[2023,12,22]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2012.10.016"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"volume-title":"Proceedings of the 12th Python in Science Conferences (SciPy'13)","author":"Bergstra J.","key":"e_1_3_2_1_3_1","unstructured":"J. Bergstra, D. Yamins, and D.D. Cox. 2013. Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms. In Proceedings of the 12th Python in Science Conferences (SciPy'13). 13--20."},{"key":"e_1_3_2_1_4_1","volume-title":"Random forests. Machine learning 45","author":"Breiman Leo","year":"2001","unstructured":"Leo Breiman. 2001. Random forests. Machine learning 45 (2001), 5--32."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022627411411"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2005.03.007"},{"key":"e_1_3_2_1_8_1","volume-title":"MM'10 - Proceedings of the ACM Multimedia 2010 International Conference, 1459--1462","author":"Eyben Florian","year":"2010","unstructured":"Florian Eyben, Martin W\u00f6llmer, and Bj\u00f6rn Schuller. 2010. openSMILE -- The Munich Versatile and Fast Open-Source Audio Feature Extractor. MM'10 - Proceedings of the ACM Multimedia 2010 International Conference, 1459--1462."},{"key":"e_1_3_2_1_9_1","volume-title":"Greedy function approximation: a gradient boosting machine. Annals of statistics","author":"Friedman Jerome H","year":"2001","unstructured":"Jerome H Friedman. 2001. Greedy function approximation: a gradient boosting machine. Annals of statistics (2001), 1189--1232."},{"key":"e_1_3_2_1_10_1","volume-title":"Multitask Prediction of Exchange-Level Annotations for Multimodal Dialogue Systems (ICMI '19)","author":"Hirano Yuki","year":"2019","unstructured":"Yuki Hirano, Shogo Okada, Haruto Nishimoto, and Kazunori Komatani. 2019. Multitask Prediction of Exchange-Level Annotations for Multimodal Dialogue Systems (ICMI '19). 85--94."},{"key":"e_1_3_2_1_11_1","volume-title":"Latent Character Model for Engagement Recognition Based on Multimodal Behaviors. In International Workshop on Spoken Dialogue Systems Technology.","author":"Inoue Koji","year":"2018","unstructured":"Koji Inoue, Divesh Lala, Katsuya Takanashi, and Tatsuya Kawahara. 2018. Latent Character Model for Engagement Recognition Based on Multimodal Behaviors. In International Workshop on Spoken Dialogue Systems Technology."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC","author":"Ishii Ryo","year":"2018","unstructured":"Ryo Ishii, Ryuichiro Higashinaka, and Junji Tomita. 2018. Predicting Nods by using Dialogue Acts in Dialogue. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)."},{"key":"e_1_3_2_1_13_1","volume-title":"Trimodal prediction of speaking and listening willingness to help improve turn-changing modeling. Frontiers in Psychology 13","author":"Ishii Ryo","year":"2022","unstructured":"Ryo Ishii, Xutong Ren, Michal Muszynski, and Louis-Philippe Morency. 2022. Trimodal prediction of speaking and listening willingness to help improve turn-changing modeling. Frontiers in Psychology 13 (2022)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2013-457"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1177\/002383099804100404"},{"key":"e_1_3_2_1_16_1","volume-title":"Proc. 2004 conference on empirical methods in natural language processing. 230--237","author":"Kudo Taku","year":"2004","unstructured":"Taku Kudo, Kaoru Yamamoto, and Yuji Matsumoto. 2004. Applying conditional random fields to Japanese morphological analysis. In Proc. 2004 conference on empirical methods in natural language processing. 230--237."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2417561"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11200"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993154"},{"key":"e_1_3_2_1_20_1","volume-title":"Modeling Japanese Praising Behavior by Analyzing Audio and Visual Behaviors. Frontiers in Computer Science 4","author":"Onishi Toshiki","year":"2022","unstructured":"Toshiki Onishi, Arisa Yamauchi, Asahi Ogushi, Ryo Ishii, Atsushi Fukayama, Takao Nakamura, and Akihiro Miyata. 2022. Modeling Japanese Praising Behavior by Analyzing Audio and Visual Behaviors. Frontiers in Computer Science 4 (2022)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"e_1_3_2_1_22_1","volume-title":"Face-to-Face Interviews for Communication Skill Measurement: A Systematic Study (ICMI '16)","author":"Rasipuram Sowmya","year":"2016","unstructured":"Sowmya Rasipuram, Pooja Rao S. B., and Dinesh Babu Jayagopi. 2016. Asynchronous Video Interviews vs. Face-to-Face Interviews for Communication Skill Measurement: A Systematic Study (ICMI '16). 370--377."},{"volume-title":"Proceedings of the Workshop on Human Judgements in Computational Linguistics. 8--16","author":"Reidsma Dennis","key":"e_1_3_2_1_23_1","unstructured":"Dennis Reidsma and Rieks op den Akker. 2008. Exploiting 'subjective' Annotations. In Proceedings of the Workshop on Human Judgements in Computational Linguistics. 8--16."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1186\/2193-1801-2-455"},{"key":"e_1_3_2_1_25_1","volume-title":"Fleiss","author":"Shrout Patrick E.","year":"1979","unstructured":"Patrick E. Shrout and Joseph L. Fleiss. 1979. Intraclass correlations: uses in assessing rater reliability. Psychological bulletin 86 2 (1979), 420--8."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Sayaka Tomimasu and Masahiro Araki. 2016. Assessment of Users' Interests in Multimodal Dialog Based on Exchange Unit (MA3HMI '16). 33--37.","DOI":"10.1145\/3011263.3011269"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2954498"}],"event":{"name":"IVA '23: ACM International Conference on Intelligent Virtual Agents","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence"],"location":"W\u00fcrzburg Germany","acronym":"IVA '23"},"container-title":["Proceedings of the 23rd ACM International Conference on Intelligent Virtual Agents"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3570945.3607304","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3570945.3607304","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T14:27:33Z","timestamp":1755872853000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3570945.3607304"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,19]]},"references-count":27,"alternative-id":["10.1145\/3570945.3607304","10.1145\/3570945"],"URL":"https:\/\/doi.org\/10.1145\/3570945.3607304","relation":{},"subject":[],"published":{"date-parts":[[2023,9,19]]},"assertion":[{"value":"2023-12-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}