HDNS-I: Infrastructure for Knowledge Linkages from Ethnography of World Societies

该项目的目标是通过提高用户根据意义而不是文字进行搜索的能力，并提供可视化和分析结果的工具，极大地提高现有世界文化人种学数据库对用户的价值。该项目将增加语义标签和数据挖掘功能，并提供相关的计算机服务，以加强eHRAF世界文化，目前包含6 500份人种学文件中的约750 000页，涉及330多个世界社会。自1949年成立以来，人类关系领域档案(HRaf)开发和改造了信息系统，以促进关于世界文化的信息的有效检索，从而使来自许多不同学科的研究人员能够更好地理解人类各种行为。该项目开发的新的语义和数据挖掘基础设施将帮助确定用户选定的广泛主题的普遍和跨文化方面，如社会情感和同理心、经济、政治以及空间和时间的利用。该数据库可以用来研究人类关于当今面临的现实问题的思想、知识、信仰和行为的各种可能性，例如：气候变化、暴力、灾害、流行病、饥饿和战争。研究文化如何以及为什么在相似的环境中变化，对于改善政策、应用科学和对人类状况的基本科学理解至关重要。这些知识对于理解日益全球化的世界是极其宝贵的。该项目将开发处理文本的高级方法，这些方法可以从部署分析和检索工具的可扩展框架中应用。该服务框架将面向初学者和高级研究人员。一些方法可以应用于远至人工智能和机器人技术的领域，使人工智能解决方案更具人性化。将通过人工智能工具应用模式提取和语言分析，为文件内容定义灵活的逻辑。该项目将产生以下结果：1)除了现有的语义标签外，通过在每个段落中确定更细粒度的主题来提高搜索结果的相关性；2)在数据库中的段落之间建立语义链接，以便研究人员能够更有效地跟踪主题线索；以及3)结果的管理、分析、可视化和汇总、用户发起的数据挖掘和模式识别的工具。这些将帮助研究人员确定和测试关于他们调查的社会的假设。除了eHRAF世界文化数据库的工作外，该项目还将提供开放获取服务，任何研究人员都可以使用这些服务来处理和分析他们自己的材料。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The goal of this project is to greatly enhance the value of an existing ethnographic database of world cultures to users by improving their ability to search by meaning rather than words, and providing tools for visualizing and analyzing their results. This project will add semantic tags and data-mining functions with associated computer services to enhance eHRAF World Cultures, presently containing about 750,000 pages from 6,500 ethnographic documents covering over 330 world societies over time. Since its inception in 1949, the Human Relations Area Files (HRAF) has developed and transformed information systems to facilitate the efficient retrieval of information on cultures of the world so that researchers from many different disciplines could arrive at better understanding of human behavior in all its variety. New semantic and data mining infrastructure developed by this project will assist in determining universal and cross-cultural aspects of a wide range of user selected topics, such as social emotion and empathy, economics, politics and use of space and time. The database can serve to examine the range of possibilities for human thought, knowledge, belief and behavior with respect to real-world problems faced today, such as: climate change; violence; disasters; epidemics; hunger; and war. Examining how and why cultures vary in similar circumstances is critical to improving policy, applied science, and basic scientific understandings of the human condition. Such knowledge is extremely valuable in understanding an increasingly globalized world. This project will develop advanced methods of working with text that can be applied from an extensible framework that deploys tools for analysis and retrieval. This services framework will be available for beginners and advanced researchers. Some methods can be applied in areas as far afield as AI and robotics, making AI solutions more human. Pattern extraction and linguistic analysis will be applied through AI tools to define a flexible logic for the contents of the documents. The project will result in: 1) improved relevance of search results though identifying finer grained topics in each paragraph in addition to the existing semantic tags; 2) establishing semantic links between the paragraphs in the database so that a researcher can follow topic trails more effectively; and 3) tools for management, analysis, visualization, and summarization of results, user initiated data mining and pattern identification. These will assist researchers identifying and testing hypotheses about the societies they investigate. In addition to working on the eHRAF World Cultures database, the project will provide open access services that any researcher can use to process and analyse their own material.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.