{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T18:59:22Z","timestamp":1776106762007,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":94,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006477","name":"National Taiwan University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006477","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Education, Taiwan"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,24]]},"DOI":"10.1145\/3708359.3712146","type":"proceedings-article","created":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T12:50:34Z","timestamp":1742388634000},"page":"1256-1271","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["SimTube: Simulating Audience Feedback on Videos using Generative AI and User Personas"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1889-1630","authenticated-orcid":false,"given":"Yu-Kai","family":"Hung","sequence":"first","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan,"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4763-7562","authenticated-orcid":false,"given":"Yun-Chien","family":"Huang","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan,"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0043-1796","authenticated-orcid":false,"given":"Ting-Yu","family":"Su","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan,"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2970-2455","authenticated-orcid":false,"given":"Yen-Ting","family":"Lin","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan,"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7712-8622","authenticated-orcid":false,"given":"Lung-Pan","family":"Cheng","sequence":"additional","affiliation":[{"name":"National Taiwan University, Taipei, Taiwan,"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9016-038X","authenticated-orcid":false,"given":"Bryan","family":"Wang","sequence":"additional","affiliation":[{"name":"Adobe Research, Seattle, Washington, USA,"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7579-6734","authenticated-orcid":false,"given":"Shao-Hua","family":"Sun","sequence":"additional","affiliation":[{"name":"Electrical Engineering, National Taiwan University, Taipei, Taiwan,"}]}],"member":"320","published-online":{"date-parts":[[2025,3,24]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_3_3_3_2","unstructured":"Arjun Panickssery and Samuel R. Bowman and Shi Feng. 2024. LLM Evaluators Recognize and Favor Their Own Generations. arxiv:https:\/\/arXiv.org\/abs\/2404.13076\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2404.13076"},{"key":"e_1_3_3_3_4_2","unstructured":"Andrei Barbu Alexander Bridge Zachary Burchill Dan Coroian Sven Dickinson Sanja Fidler Aaron Michaux Sam Mussman Siddharth Narayanaswamy Dhaval Salvi Lara Schmidt Jiangnan Shangguan Jeffrey\u00a0Mark Siskind Jarrell Waggoner Song Wang Jinlian Wei Yifan Yin and Zhiqi Zhang. 2012. Video In Sentences Out. arxiv:https:\/\/arXiv.org\/abs\/1204.2742\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1204.2742"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","unstructured":"Kobus Barnard. 2016. Computational Methods for Integrating Vision and Language. Synthesis Lectures on Computer Vision 6 (04 2016) 1\u2013227. 10.2200\/S00705ED1V01Y201602COV007","DOI":"10.2200\/S00705ED1V01Y201602COV007"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642406"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.220"},{"key":"e_1_3_3_3_8_2","unstructured":"Tom\u00a0B Brown. 2020. Language models are few-shot learners. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.14165 (2020)."},{"key":"e_1_3_3_3_9_2","unstructured":"S\u00e9bastien Bubeck Varun Chandrasekaran Ronen Eldan Johannes Gehrke Eric Horvitz Ece Kamar Peter Lee Yin\u00a0Tat Lee Yuanzhi Li Scott Lundberg Harsha Nori Hamid Palangi Marco\u00a0Tulio Ribeiro and Yi Zhang. 2023. Sparks of Artificial General Intelligence: Early experiments with GPT-4. arxiv:https:\/\/arXiv.org\/abs\/2303.12712\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2303.12712"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-3402"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","unstructured":"Sorina Chelaru Claudia Orellana-Rodriguez and Ismail\u00a0Sengor Altingovde. 2014. How useful is social feedback for learning to rank YouTube videos? World Wide Web 17 5 (2014) 997\u20131025. 10.1007\/s11280-013-0258-9","DOI":"10.1007\/s11280-013-0258-9"},{"key":"e_1_3_3_3_12_2","unstructured":"Lin Chen Xilin Wei Jinsong Li Xiaoyi Dong Pan Zhang Yuhang Zang Zehui Chen Haodong Duan Bin Lin Zhenyu Tang Li Yuan Yu Qiao Dahua Lin Feng Zhao and Jiaqi Wang. 2024. ShareGPT4Video: Improving Video Understanding and Generation with Better Captions. arxiv:https:\/\/arXiv.org\/abs\/2406.04325\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2406.04325"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"crossref","unstructured":"Ahmed\u00a0Kharrufa Colin\u00a0Dodds. 2024. Show-and-Tell: An Interface for Delivering Rich Feedback upon Creative Media Artefacts. Multimodal Technol. Interact (2024). https:\/\/www.mdpi.com\/2414-4088\/8\/3\/23","DOI":"10.3390\/mti8030023"},{"key":"e_1_3_3_3_14_2","unstructured":"Digital Marketing Institute. 2024. 14 Ways to Grow Your YouTube Channel. https:\/\/digitalmarketinginstitute.com\/. https:\/\/digitalmarketinginstitute.com\/blog\/10-ways-to-grow-your-youtube-channel-in-2018 Accessed: 2024-10-01."},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"crossref","unstructured":"Pierre Dognin Igor Melnyk Youssef Mroueh Inkit Padhi Mattia Rigotti Jarret Ross Yair Schiff Richard\u00a0A Young and Brian Belgodere. 2022. Image captioning as an assistive technology: Lessons learned from vizwiz 2020 challenge. Journal of Artificial Intelligence Research 73 (2022) 437\u2013459.","DOI":"10.1613\/jair.1.13113"},{"key":"e_1_3_3_3_16_2","unstructured":"Chaoqun Duan Lei Cui Shuming Ma Furu Wei Conghui Zhu and Tiejun Zhao. 2020. Multimodal Matching Transformer for Live Commenting. arxiv:https:\/\/arXiv.org\/abs\/2002.02649\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2002.02649"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","unstructured":"Ilana Dubovi and Iris Tabak. 2020. An empirical analysis of knowledge co-construction in YouTube comments. Computers & Education 156 (2020) 103939. 10.1016\/j.compedu.2020.103939","DOI":"10.1016\/j.compedu.2020.103939"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3635636.3656183"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3131785.3131791"},{"key":"e_1_3_3_3_21_2","unstructured":"Shansan Gong Mukai Li Jiangtao Feng Zhiyong Wu and LingPeng Kong. 2022. Diffuseq: Sequence to sequence text generation with diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.08933 (2022)."},{"key":"e_1_3_3_3_22_2","unstructured":"Tanya Goyal Junyi\u00a0Jessy Li and Greg Durrett. 2022. News Summarization and Evaluation in the Era of GPT-3. ArXiv abs\/2209.12356 (2022). https:\/\/api.semanticscholar.org\/CorpusID:252532176"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580688"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","unstructured":"John Hattie and Helen Timperley. 2007. The Power of Feedback. Review of Educational Research 77 1 (2007) 81\u2013112. 10.3102\/003465430298487 arXiv:10.3102\/003465430298487","DOI":"10.3102\/003465430298487"},{"key":"e_1_3_3_3_28_2","unstructured":"Maria Holmbom. 2015. The YouTuber: A Qualitative Study of Popular Content Creators. Dissertation. Ume\u00e5 University. https:\/\/urn.kb.se\/resolve?urn=urn:nbn:se:umu:diva-105388"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","unstructured":"MD.\u00a0Zakir Hossain Ferdous Sohel Mohd\u00a0Fairuz Shiratuddin and Hamid Laga. 2019. A Comprehensive Survey of Deep Learning for Image Captioning. ACM Comput. Surv. 51 6 Article 118 (feb 2019) 36\u00a0pages. 10.1145\/3295748","DOI":"10.1145\/3295748"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","unstructured":"Tasos Hovardas Olia\u00a0E. Tsivitanidou and Zacharias\u00a0C. Zacharia. 2014. Peer versus expert feedback: An investigation of the quality of peer feedback among secondary school students. Computers & Education 71 (2014) 133\u2013152. 10.1016\/j.compedu.2013.09.019","DOI":"10.1016\/j.compedu.2013.09.019"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00769"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1147"},{"key":"e_1_3_3_3_33_2","first-page":"1","volume-title":"Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems","author":"Huh Mina","unstructured":"Mina Huh, Saelyne Yang, and Yi-Hao Peng. [n.d.]. Xiang\u2019Anthony\u2019Chen, Young-Ho Kim, and Amy Pavel. 2023. AVscript: Accessible Video Editing with Audio-Visual Scripts. In Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. 1\u201317."},{"key":"e_1_3_3_3_34_2","unstructured":"Hang Jiang Xiajie Zhang Xubo Cao Cynthia Breazeal Deb Roy and Jad Kabbara. 2024. PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits. arxiv:https:\/\/arXiv.org\/abs\/2305.02547\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2305.02547"},{"key":"e_1_3_3_3_35_2","unstructured":"josepmartins. [n.d.]. boring-avatar. https:\/\/github.com\/boringdesigners\/boring-avatars"},{"key":"e_1_3_3_3_36_2","unstructured":"Taehyeong Kim Min-Oh Heo Seonil Son Kyoung-Wha Park and Byoung-Tak Zhang. 2019. GLAC Net: GLocal Attention Cascading Networks for Multi-image Cued Story Generation. arxiv:https:\/\/arXiv.org\/abs\/1805.10973\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1805.10973"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"crossref","unstructured":"Avraham\u00a0N Kluger and Angelo DeNisi. 1996. The effects of feedback interventions on performance: a historical review a meta-analysis and a preliminary feedback intervention theory. Psychological bulletin 119 2 (1996) 254.","DOI":"10.1037\/\/0033-2909.119.2.254"},{"key":"e_1_3_3_3_38_2","unstructured":"Saydulu Kolasani. 2023. Optimizing Natural Language Processing Large Language Models (LLMs) for Efficient Customer Service and hyper-personalization to enable sustainable growth and revenue. Transactions on Latest Trends in Artificial Intelligence 4 4 (2023). https:\/\/ijsdcs.com\/index.php\/TLAI\/article\/view\/476"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/2724660.2724670"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995466"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.5555\/2390524.2390575"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502030"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/2016911.2016934"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1014"},{"key":"e_1_3_3_3_45_2","first-page":"74","volume-title":"Text summarization branches out","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out. 74\u201381."},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.nlp4convai-1.5"},{"key":"e_1_3_3_3_47_2","volume-title":"International Conference on Learning Representations","author":"Liu Max","year":"2025","unstructured":"Max Liu, Chan-Hung Yu, Wei-Hsu Lee, Cheng-Wei Hung, Yen-Chun Chen, and Shao-Hua Sun. 2025. Synthesizing Programmatic Reinforcement Learning Policies with Large Language Model Guided Search. In International Conference on Learning Representations."},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"crossref","unstructured":"Yang Liu Dan Iter Yichong Xu Shuohang Wang Ruochen Xu and Chenguang Zhu. 2023. G-eval: Nlg evaluation using gpt-4 with better human alignment. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.16634 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"e_1_3_3_3_49_2","volume-title":"Conference on Language Modeling","author":"Lu Li-Chun","year":"2024","unstructured":"Li-Chun Lu, Shou-Jen Chen, Tsung-Min Pai, Chan-Hung Yu, Hung-Yi Lee, and Shao-Hua Sun. 2024. LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play. In Conference on Language Modeling."},{"key":"e_1_3_3_3_50_2","unstructured":"Pan Lu Swaroop Mishra Tanglin Xia Liang Qiu Kai-Wei Chang Song-Chun Zhu Oyvind Tafjord Peter Clark and Ashwin Kalyan. 2022. Learn to explain: Multimodal reasoning via thought chains for science question answering. Advances in Neural Information Processing Systems 35 (2022) 2507\u20132521."},{"key":"e_1_3_3_3_51_2","unstructured":"Shuming Ma Lei Cui Damai Dai Furu Wei and Xu Sun. 2018. LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts. arxiv:https:\/\/arXiv.org\/abs\/1809.04938\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1809.04938"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","unstructured":"Amy Madden Ian Ruthven and David Mcmenemy. 2013. A classification scheme for content analyses of YouTube video comments. Journal of Documentation 69 (09 2013). 10.1108\/JD-06-2012-0078","DOI":"10.1108\/JD-06-2012-0078"},{"key":"e_1_3_3_3_53_2","unstructured":"Ali Malik Mike Wu Vrinda Vasavada Jinpeng Song Madison Coots John Mitchell Noah Goodman and Chris Piech. 2021. Generative Grading: Near Human-level Accuracy for Automated Feedback on Richly Structured Problems. arxiv:https:\/\/arXiv.org\/abs\/1905.09916\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/1905.09916"},{"key":"e_1_3_3_3_54_2","unstructured":"Meta. 2022. PersonaChat. https:\/\/www.kaggle.com\/datasets\/atharvjairath\/personachat Accessed: 2024-10-01."},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581225"},{"key":"e_1_3_3_3_56_2","series-title":"(EACL \u201912)","first-page":"747","volume-title":"Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics","author":"Mitchell Margaret","year":"2012","unstructured":"Margaret Mitchell, Xufeng Han, Jesse Dodge, Alyssa Mensch, Amit Goyal, Alex Berg, Kota Yamaguchi, Tamara Berg, Karl Stratos, and Hal Daum\u00e9. 2012. Midge: generating image descriptions from computer vision detections. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics (Avignon, France) (EACL \u201912). Association for Computational Linguistics, USA, 747\u2013756."},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","unstructured":"Hamed Nilforoshan and Eugene Wu. 2018. Leveraging Quality Prediction Models for Automatic Writing Feedback. Proceedings of the International AAAI Conference on Web and Social Media 12 1 (Jun. 2018). 10.1609\/icwsm.v12i1.14998","DOI":"10.1609\/icwsm.v12i1.14998"},{"key":"e_1_3_3_3_58_2","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt and Sam\u00a0Altman et. al.2023. GPT-4 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2303.08774\u00a0[cs.CL]"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781003251323"},{"key":"e_1_3_3_3_60_2","unstructured":"Keivalya Pandya and Mehfuza Holia. 2023. Automating Customer Service using LangChain: Building custom open-source GPT Chatbot for organizations. arxiv:https:\/\/arXiv.org\/abs\/2310.05421\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.05421"},{"key":"e_1_3_3_3_61_2","unstructured":"Joon\u00a0Sung Park Joseph\u00a0C. O\u2019Brien Carrie\u00a0J. Cai Meredith\u00a0Ringel Morris Percy Liang and Michael\u00a0S. Bernstein. 2023. Generative Agents: Interactive Simulacra of Human Behavior. arxiv:https:\/\/arXiv.org\/abs\/2304.03442\u00a0[cs.HC]"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3526113.3545616"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/2984511.2984552"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-62362-2_39"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3502718.3524762"},{"key":"e_1_3_3_3_66_2","unstructured":"Alec Radford Jong\u00a0Wook Kim Tao Xu Greg Brockman Christine McLeavey and Ilya Sutskever. 2022. Robust Speech Recognition via Large-Scale Weak Supervision. arxiv:https:\/\/arXiv.org\/abs\/2212.04356\u00a0[eess.AS]"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/964696.964708"},{"key":"e_1_3_3_3_68_2","unstructured":"Yunfan Shao Linyang Li Junqi Dai and Xipeng Qiu. 2023. Character-LLM: A Trainable Agent for Role-Playing. arxiv:https:\/\/arXiv.org\/abs\/2310.10158\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.10158"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.548"},{"key":"e_1_3_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772781"},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00825-3_13"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"crossref","unstructured":"Jingkuan Song Yuyu Guo Lianli Gao Xuelong Li Alan Hanjalic and Heng\u00a0Tao Shen. 2018. From deterministic to generative: Multimodal stochastic RNNs for video captioning. IEEE transactions on neural networks and learning systems 30 10 (2018) 3047\u20133058.","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"e_1_3_3_3_73_2","unstructured":"SSA. 2023. USA Baby Name Dataset. https:\/\/www.ssa.gov\/OACT\/babynames\/limits.html"},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","unstructured":"Marie Stevenson and Aek Phakiti. 2014. The effects of computer-generated feedback on the quality of writing. Assessing Writing 19 (2014) 51\u201365. 10.1016\/j.asw.2013.11.007Feedback in Writing: Issues and Challenges.","DOI":"10.1016\/j.asw.2013.11.007"},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.88"},{"key":"e_1_3_3_3_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/2072298.2072411"},{"key":"e_1_3_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"e_1_3_3_3_78_2","doi-asserted-by":"crossref","unstructured":"Mike Thelwall Pardeep Sud and Farida Vis. 2012. Commenting on YouTube videos: From Guatemalan rock to el big bang. Journal of the American society for information science and technology 63 3 (2012) 616\u2013629.","DOI":"10.1002\/asi.21679"},{"key":"e_1_3_3_3_79_2","unstructured":"Thematic Analysis Inc.2024. Thematic Comment Analysis. https:\/\/getthematic.com\/product\/comment-analyzer\/ Accessed: 2024-10-01."},{"key":"e_1_3_3_3_80_2","unstructured":"Yu-Min Tseng Yu-Chao Huang Teng-Yun Hsiao Wei-Lin Chen Chao-Wei Huang Yu Meng and Yun-Nung Chen. 2024. Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization. arxiv:https:\/\/arXiv.org\/abs\/2406.01171\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2406.01171"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642839"},{"key":"e_1_3_3_3_82_2","unstructured":"VEED. 2024. VEED. https:\/\/www.veed.io\/ Accessed: 2024-10-01."},{"key":"e_1_3_3_3_83_2","unstructured":"Bryan Wang Yuliang Li Zhaoyang Lv Haijun Xia Yan Xu and Raj Sodhi. 2024. LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing. arxiv:https:\/\/arXiv.org\/abs\/2402.10294\u00a0[cs.HC] https:\/\/arxiv.org\/abs\/2402.10294"},{"key":"e_1_3_3_3_84_2","doi-asserted-by":"crossref","unstructured":"Yaqing Wang Quanming Yao James\u00a0T Kwok and Lionel\u00a0M Ni. 2020. Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur) 53 3 (2020) 1\u201334.","DOI":"10.1145\/3386252"},{"key":"e_1_3_3_3_85_2","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022) 24824\u201324837."},{"key":"e_1_3_3_3_86_2","unstructured":"Hao Wu Gareth J.\u00a0F. Jones and Francois Pitie. 2020. Response to LiveBot: Generating Live Video Comments Based on Visual and Textual Contexts. arxiv:https:\/\/arXiv.org\/abs\/2006.03022\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2006.03022"},{"key":"e_1_3_3_3_87_2","doi-asserted-by":"crossref","unstructured":"Michihiro Yasunaga Jure Leskovec and Percy Liang. 2022. Linkbert: Pretraining language models with document links. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2203.15827 (2022).","DOI":"10.18653\/v1\/2022.acl-long.551"},{"key":"e_1_3_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/2642918.2647390"},{"key":"e_1_3_3_3_89_2","unstructured":"YouTube. 2023. Made on YouTube. https:\/\/blog.youtube\/news-and-events\/made-on-youtube-2023\/"},{"key":"e_1_3_3_3_90_2","doi-asserted-by":"publisher","unstructured":"Kuo-Hao Zeng Tseng-Hung Chen Ching-Yao Chuang Yuan-Hong Liao Juan\u00a0Carlos Niebles and Min Sun. 2017. Leveraging Video Descriptions to Learn Video Question Answering. Proceedings of the AAAI Conference on Artificial Intelligence 31 1 (Feb. 2017). 10.1609\/aaai.v31i1.11238","DOI":"10.1609\/aaai.v31i1.11238"},{"key":"e_1_3_3_3_91_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-75765-6_55"},{"key":"e_1_3_3_3_92_2","volume-title":"Conference on Robot Learning","author":"Zhang Jesse","year":"2023","unstructured":"Jesse Zhang, Karl\u00a0Pertsch Jiahui\u00a0Zhang, Ziyi Liu, Xiang Ren, Minsuk Chang, Shao-Hua Sun, and Joseph\u00a0J. Lim. 2023. Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance. In Conference on Robot Learning."},{"key":"e_1_3_3_3_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00862"},{"key":"e_1_3_3_3_94_2","volume-title":"International Conference on Learning Representations","author":"Zhang* Tianyi","year":"2020","unstructured":"Tianyi Zhang*, Varsha Kishore*, Felix Wu*, Kilian\u00a0Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SkeHuCVFDr"},{"key":"e_1_3_3_3_95_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210080"}],"event":{"name":"IUI '25: 30th International Conference on Intelligent User Interfaces","location":"Cagliari Italy","acronym":"IUI '25","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 30th International Conference on Intelligent User Interfaces"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708359.3712146","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3708359.3712146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:57:06Z","timestamp":1750298226000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3708359.3712146"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":94,"alternative-id":["10.1145\/3708359.3712146","10.1145\/3708359"],"URL":"https:\/\/doi.org\/10.1145\/3708359.3712146","relation":{},"subject":[],"published":{"date-parts":[[2025,3,24]]},"assertion":[{"value":"2025-03-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}