[幻灯片改编自加州大学伯克利分校 CS188 人工智能入门课上的 Dan Klein、Pieter Abbeel、Stuart Russell 等人的幻灯片。所有材料均可在 http://ai.berkeley.edu 上找到。]
通过应用人工智能对核电站运行产生的大量文本信息进行搜索和分类,我们有望提高搜索效率,在短时间内找到合适的信息,并通过自动分类提高信息分析的精细度。为此,我们使用基于向量空间模型的人工智能语义检索来检索信息,评估其有效性并提取问题。
Background: The COVID-19 pandemic, declared in March 2020, profoundly affected global health, societal, and economic frameworks. Vaccination became a crucial tactic in combating the virus. Simultaneously, the pandemic likely underscored the internet's role as a vital resource for seeking health information. The proliferation of misinformation on social media was observed, potentially influencing vaccination decisions and timing. Objective: This study aimed to explore the relationship between COVID-19 vaccination rates, including the timing of vaccination, and reliance on internet-based information sources in Japan. Methods: Using a cross-sectional study design using a subset of panel data, this nationwide survey was conducted in 7 waves. A total of 10,000 participants were randomly selected through an internet survey firm, narrowing down to 8724 after applying inclusion and exclusion criteria. The primary outcome was the COVID-19 vaccination date, divided into vaccinated versus unvaccinated and early versus late vaccination groups. The main exposure variable was the use of internet-based information sources. Control variables included gender, family structure, education level, employment status, household income, eligibility for priority COVID-19 vaccination due to pre-existing medical conditions, and a health literacy scale score. Two regression analyses using generalized estimating equations accounted for prefecture-specific correlations, focusing on vaccination status and timing. In addition, chi-square tests assessed the relationship between each information source and vaccination rates. Results: Representing a cross-section of the Japanese population, the regression analysis found a significant association between internet information seeking and higher vaccination rates (adjusted odds ratio [aOR] 1.42 for those younger than 65 years; aOR 1.66 for those aged 65 years and older). However, no significant link was found regarding vaccination timing. Chi-square tests showed positive associations with vaccination for television, government web pages, and web news, whereas blogs and some social networking sites were negatively correlated. Conclusions: Internet-based information seeking is positively linked to COVID-19 vaccination rates in Japan, underscoring the significant influence of online information on public health decisions. Nonetheless, certain online information sources, including blogs and some social networks, negatively affected vaccination rates, warranting caution in their use and recognition. The study highlights the critical role of credible online sources in public health communication and the challenge of combating
近年来,数字革命极大地改变了医疗保健格局,彻底改变了医疗服务的可及性、医疗保健服务提供方式、患者参与度以及在线健康信息寻求行为 (HISB) 的增长。由于这些所谓的好处,数字访问越来越被认为是健康的社会决定因素 ( 1 )。然而,“数字鸿沟”是指对计算机和互联网等信息和通信技术的不同访问 ( 2 ),可能会导致更大的健康不平等 ( 3 )。多项研究表明,在历史上服务不足的群体中,包括少数族裔/民族、英语水平有限、教育水平较低、年龄较大、低收入家庭和农村居民,互联网访问和使用健康信息的可能性降低 ( 4 , 5 )。然而,2021 年的一项调查显示,差距正在迅速缩小,85% 的白人受访者、83% 的黑人受访者、85% 的西班牙裔受访者和 76% 的收入低于 30,000 美元的受访者表示拥有智能手机 ( 6 )。
信息访问系统正变得越来越复杂,我们对用户在信息搜索过程中的行为的理解主要来自于定性方法,比如观察性研究或调查。利用传感技术的进步,我们的研究旨在用生理信号来表征用户行为,特别是与认知负荷、情感唤醒和效价有关的行为。我们对 26 名参与者进行了一项受控实验室研究,并收集了包括皮电活动、光电容积图、脑电图和瞳孔反应在内的数据。本研究从四个阶段探讨了信息搜索:信息需求 (IN) 的实现、查询公式 (QF)、查询提交 (QS) 和相关性判断 (RJ)。我们还包括不同的交互模式来表示现代系统,例如通过文本输入或口头表达的 QS,以及通过文本或音频信息的 RJ。我们分析了这些阶段的生理信号,并报告了成对非参数重复测量统计检验的结果。结果表明,参与者在 IN 时会经历明显更高的认知负荷,并且警觉性略有增加,而 QF 需要更高的注意力。QS 比 QF 需要更高的认知负荷。RJ 时的情感反应比 QS 或 IN 更明显,这表明在知识差距得到解决后,兴趣和参与度会更高。据我们所知,这是第一项采用更细致入微的生理信号定量分析来探索搜索过程中用户行为的研究。我们的研究结果为用户在信息搜索过程中的行为和情绪反应提供了宝贵的见解。我们相信,我们提出的方法可以为更复杂过程的特征提供信息,例如对话式信息搜索。
课程概述 人工智能 (AI) 是几乎所有 21 世纪技术突破的基础。从自动驾驶汽车到自动翻译应用程序,AI 正在改变我们社会的方方面面,并在医疗保健、教育、金融、交通和环境可持续性等领域有着广泛的应用。在本课程中,我们将揭示“自动推理”的核心思想,这些思想使我们能够理解 AI 的基础主题。具体来说,我们将探索和解读以下主题: 模块 1(搜索) 无信息搜索、有信息搜索、本地搜索、对抗性搜索 模块 2(计划和调度) 约束满足、约束优化 模块 3(不确定性下的决策) 马尔可夫决策过程、强化学习 模块 4(图模型) 贝叶斯网络、隐马尔可夫模型 模块 5(机器学习) 监督学习、无监督学习、深度学习