DanModCap：为视频分享平台设计一种利用大语言模型生成冲击字幕的弹幕管理工具
DanModCap: Designing a Danmaku Moderation Tool for Video-Sharing Platforms that Leverages Impact Captions with Large Language Models
AI总结：
本文提出弹幕管理工具DanModCap，利用大语言模型将弹幕分析结果转化为冲击字幕，以主动引导用户产生亲社会行为并减少负面情绪。
摘要：
在线视频平台因其支持信息消费与分享以及提供多样化社交互动的能力而日益受到欢迎。弹幕是一种将用户评论实时叠加在视频上的评论功能，已被发现能够提升用户参与度，但弹幕的使用也可能导致有害行为和不当评论。为解决这些问题，我们提出了一种受冲击字幕启发的主动管理方法。冲击字幕是一种用于东亚综艺节目的视觉技术，它结合文本内容与视觉元素来构建情感和认知共鸣。在本研究背景下，冲击字幕被用于引导观众参与积极的弹幕相关活动，并激发更多亲社会行为。利用冲击字幕，我们开发了DanModCap，这是一种管理工具，能够收集和分析弹幕，并将其作为大型生成式语言模型的输入以生成冲击字幕。我们对DanModCap的评估表明，冲击字幕减少了负面对抗性情绪，增强了用户分享积极内容的意愿，并在弹幕社交行为中激发了自我控制，从而促进主动的社区维护行为。我们的方法凸显了在大规模直播内容场景中使用大语言模型支持的内容管理方法进行主动管理的优势。
英文摘要：
Online video platforms have gained increased popularity due to their ability to support information consumption and sharing and the diverse social interactions they afford. Danmaku, a real-time commentary feature that overlays user comments on a video, has been found to improve user engagement, however, the use of Danmaku can lead to toxic behaviors and inappropriate comments. To address these issues, we propose a proactive moderation approach inspired by Impact Captions, a visual technique used in East Asian variety shows. Impact Captions combine textual content and visual elements to construct emotional and cognitive resonance. Within the context of this work, Impact Captions were used to guide viewers towards positive Danmaku-related activities and elicit more pro-social behaviors. Leveraging Impact Captions, we developed DanModCap, an moderation tool that collected and analyzed Danmaku and used it as input to large generative language models to produce Impact Captions. Our evaluation of DanModCap demonstrated that Impact Captions reduced negative antagonistic emotions, increased users' desire to share positive content, and elicited self-control in Danmaku social action to fostering proactive community maintenance behaviors. Our approach highlights the benefits of using LLM-supported content moderation methods for proactive moderation in a large-scale live content contexts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
