BIGDATA: IA: Multiplatform, Multilingual, and Multimodal Tools for Analyzing Public Communication in over 100 Languages

在当今的信息时代，了解世界各地的公共交流对美国的政策和外交非常重要。研究的挑战是收集、分析和解释全球范围内呈现的信息，创建高速、海量、视角、语言和平台多种多样的大数据。世界范围内研究文字和视觉公共信息的分析方法受到语言障碍的限制。该项目旨在通过开发有效利用自然语言处理、机器学习和计算机视觉工具的方法来解决国际公共信息流领域的数据分析问题。这项研究将涉及收集源自美国并在世界各地报道的多语言、多平台和多模式的文本和图像语料库，开发一种可有效扩展的交互式预算高效的专家和众筹人员注释方法，使用机器学习和深度学习技术，利用多语言和多模式表示法来开发数据分析工具，用于实体和框架识别、实体和框架的情感分析，以及管理多种语言的平衡实时内容集合。该项目预计将为社会科学家和其他人提供分析工具，以便更好地研究公共传播的国际流动。带注释的数据将提供培训和基准数据集，可以推动多种语言的实体和框架识别、情感分析和其他相关自然语言处理任务的研究。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。

In today's information age, understanding public communication flows around the world is important to United States policy and diplomacy. The challenge for research is to collect, analyze, and interpret information as it is presented worldwide, creating big data that is flowing at high velocity, in large volumes, with much variety in perspective, language, and platforms. Analytic methods for studying textual and visual public information worldwide are limited by language hurdles. This project aims to solve data analytics problems in the domain of international public information flows by developing methods that effectively leverage natural language processing, machine learning, and computer vision tools. This research will involve collecting multilingual, multiplatform, and multimodal corpora of text and images originating in the U.S. and reported worldwide, developing an interactive budget-efficient methodology for annotation by experts and crowdworkers that scales effectively, using machine learning and deep learning techniques that exploit multilingual and multimodal representations to develop data analytics tools for entity and frame recognition, sentiment analysis of entities and frames, and curating balanced real-time content collections for many languages. This project is expected to generate analytical tools for social scientists and others to better examine the international flow of public communications. The annotated data will provide training and benchmark datasets that can propel research in entity and frame recognition, sentiment analysis, and other related natural language processing tasks for many languages.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.