arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.16490cs.CLcs.AIcs.CY
收藏

探索新闻意图及其应用:一种理论驱动的方法

Exploring news intent and its application: A theory-driven approach

Media Synthesis and Forensics Lab, Institute of Computing Technology, Chinese Academy of Sciences(计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);University of Macau(澳门大学);Communication University of China(中国传媒大学)

Zhengjia Wang, Danding Wang, Qiang Sheng, Juan Cao, Siyuan Ma, Haonan Cheng

AI总结:

该研究针对新闻意图缺乏结构化研究的问题,基于跨学科研究提出概念解构式新闻意图理解框架NINT,构建新数据集,验证了意图辅助可提升假新闻检测等新闻任务效果,为相关领域提供参考。

摘要:

理解信息背后的意图至关重要。然而,新闻作为公共话语媒介,目前仍缺乏对感知新闻意图及其应用的系统性结构化研究。为推动该领域发展,本文回顾了关于意向性行为的跨学科研究,提出了一种基于概念解构的新闻意图理解框架NINT。该框架识别了意图的组成要素,助力实现新闻意图及其应用的结构化表征。基于NINT,我们构建了一个全新的意图感知数据集。此外,我们探究了意图辅助在新闻相关任务中的潜力,例如在假新闻检测任务中取得了显著提升(macF1提升2.2%)。我们希望本研究结果能为基于行动的意图认知与计算社会科学研究提供有价值的见解。

英文摘要:

Understanding the intent behind information is crucial. However, news as a medium of public discourse still lacks a structured investigation of perceived news intent and its application. To advance this field, this paper reviews interdisciplinary studies on intentional action and introduces a conceptual deconstruction-based news intent understanding framework (NINT). This framework identifies the components of intent, facilitating a structured representation of news intent and its applications. Building upon NINT, we contribute a new intent perception dataset. Moreover, we investigate the potential of intent assistance on news-related tasks, such as significant improvement (+2.2% macF1) in the task of fake news detection. We hope that our findings will provide valuable insights into action-based intent cognition and computational social science.

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。

↑